← 返回 Skills 市场

Conference Abstract Adaptor

Name: Conference Abstract Adaptor
Author: aipoch-ai

作者 AIpoch · GitHub ↗ · v0.1.0 · MIT-0

cross-platform ⚠ suspicious

208

总下载

当前安装

版本数

在 OpenClaw 中安装

/install conference-abstract-adaptor

功能描述

Adapt abstracts to meet specific conference word limits and formats

使用说明 (SKILL.md)

Conference Abstract Adaptor

Conference-specific abstract formatting.

Use Cases

Multi-conference submissions
Word count compliance
Format standardization
Deadline management

Parameters

Parameter	Type	Default	Required	Description
`--abstract`, `-a`	string	-	Yes	Abstract text file path
`--conference`, `-c`	string	-	Yes	Target conference (ASGCT, ASCO, SfN, AACR, ASM)
`--output`, `-o`	string	-	No	Output file path
`--list-conferences`, `-l`	flag	-	No	List supported conferences

Usage

# Adapt abstract for ASCO
python scripts/main.py --abstract my_abstract.txt --conference ASCO

# Save adapted abstract to file
python scripts/main.py --abstract my_abstract.txt --conference ASGCT --output adapted.txt

# List all supported conferences
python scripts/main.py --list-conferences

Supported Conferences

Conference	Word Limit	Format
ASGCT	250 words	Structured (Background/Methods/Results/Conclusion)
ASCO	260 words	Structured (Background/Methods/Results/Conclusion)
SfN	2000 chars	Single abstract
AACR	300 words	Structured (Background/Methods/Results/Conclusion)
ASM	300 words	Single abstract

Returns

Reformatted abstract
Word count verification
Required sections checklist
Submission-ready text

Risk Assessment

Risk Indicator	Assessment	Level
Code Execution	Python/R scripts executed locally	Medium
Network Access	No external API calls	Low
File System Access	Read input files, write output files	Medium
Instruction Tampering	Standard prompt guidelines	Low
Data Exposure	Output files saved to workspace	Low

Security Checklist

No hardcoded credentials or API keys
No unauthorized file system access (../)
Output does not expose sensitive information
Prompt injection protections in place
Input file paths validated (no ../ traversal)
Output directory restricted to workspace
Script execution in sandboxed environment
Error messages sanitized (no stack traces exposed)
Dependencies audited

Prerequisites

No additional Python packages required.

Evaluation Criteria

Success Metrics

Successfully executes main functionality
Output meets quality standards
Handles edge cases gracefully
Performance is acceptable

Test Cases

Basic Functionality: Standard input → Expected output
Edge Case: Invalid input → Graceful error handling
Performance: Large dataset → Acceptable processing time

Lifecycle Status

Current Stage: Draft
Next Review Date: 2026-03-06
Known Issues: None
Planned Improvements:
- Performance optimization
- Additional feature support

安全使用建议

This skill appears to implement the advertised functionality, but it is draft-quality and contains some security gaps you should consider before using it on sensitive data: - The script reads whatever path you pass; it does not check for '../' traversal, canonicalize paths, or restrict input to a safe workspace. A malicious or mistaken path argument could expose sensitive local files. Only run with input files you control, or add path validation (e.g., resolve realpath and ensure it is under an allowed directory). - The script lacks try/except around file operations and will print raw Python stack traces on errors (SKILL.md promised sanitized error messages). Consider adding exception handling to avoid leaking filesystem layout or other details. - There is no sandboxing or execution isolation required by the skill; run it in an isolated environment if abstracts contain sensitive or unpublished content. - The SKILL.md security checklist items (no traversal, sandboxing, sanitized errors) are NOT enforced by the code — treat them as TODOs, not guarantees. If you want to proceed: review or run the included scripts/main.py locally in a sandbox, add input path validation and error handling, and test with non-sensitive files first. If you need, ask the author to update the code to enforce workspace-restricted file access and to catch errors before installing or invoking this skill in production.

功能分析

Type: OpenClaw Skill Name: conference-abstract-adaptor Version: 0.1.0 The skill is designed to reformat conference abstracts but is classified as suspicious due to unmitigated path traversal vulnerabilities in `scripts/main.py`, where user-provided file paths are passed directly to `open()` for reading and writing without sanitization. Additionally, the `SKILL.md` documentation acknowledges these risks in its security checklist (e.g., 'Input file paths validated', 'Output directory restricted') but leaves them as uncompleted tasks, confirming that the tool possesses risky file system capabilities without the necessary security safeguards.

能力评估

✓ Purpose & Capability

The name/description (adapt abstracts to conference formats) aligns with the included script: scripts/main.py reads an input file, parses/structures text, enforces/estimates word/char limits, and writes an adapted output. No unrelated binaries, env vars, or services are requested.

⚠ Instruction Scope

SKILL.md instructs running python scripts/main.py with file paths and claims input validation and sandboxing in the security checklist, but the runtime instructions grant the agent (or user) permission to supply arbitrary filesystem paths. The script opens files directly (open(args.abstract)) with no path canonicalization or traversal checks and does not catch exceptions, so it can read arbitrary local files and will surface stack traces on errors. This is scope creep relative to the claimed 'No unauthorized file system access' and 'Input file paths validated' checklist items.

✓ Install Mechanism

No install spec; skill is instruction-only with one included Python script. Nothing is downloaded or executed from external URLs, and no packages are installed. This is low-risk from an install perspective.

✓ Credentials

No environment variables, credentials, or config paths are requested. The requested capabilities (reading an input text file and optionally writing an output file) are proportionate to the stated purpose.

✓ Persistence & Privilege

Skill does not request persistent or elevated privileges (always:false). It does not modify other skills or system configuration. It runs as an ad-hoc script when invoked.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install conference-abstract-adaptor
安装完成后，直接呼叫该 Skill 的名称或使用 /conference-abstract-adaptor 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.1.0

Initial release. - Provides a tool for adapting research abstracts to meet specific conference word limits and formatting requirements. - Supports multiple conferences, including ASGCT, ASCO, SfN, AACR, and ASM, with built-in word/character limits and format checks. - Accepts input abstract files and outputs submission-ready, reformatted text, including section verification and word count compliance. - Includes a security and risk assessment checklist. - No extra package dependencies required.

元数据

Slug conference-abstract-adaptor

版本 0.1.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题