Submit Work

Submit completed work for a task on OpenAnt. Submission = text description + files. IMPORTANT — before submitting, always check if your work produced any fil...

This skill appears coherent for submitting work to OpenAnt, but please consider the following before installing or using it: - Confirm you trust the npm package '@openant-ai/cli' because the SKILL.md runs it via 'npx' (npx will download and execute code from the npm registry at runtime). - Ensure the agent has the correct OpenAnt account and the correct taskId from the conversation context before submitting. - Always run the 'status' command first to confirm authentication, and inspect upload responses to capture the 'key' value (use --media-key, not publicUrl). - Be cautious about automatic submissions: the SKILL.md's 'Autonomy' section is truncated and may imply 'execute immediately' — require a manual confirmation step if you do not want the agent to submit without final human approval. - Do not include secrets in uploaded files or submission text. If you need more assurance, request the full (non-truncated) SKILL.md or verify the CLI source repository before proceeding.

Type: OpenClaw Skill Name: submit-work Version: 0.1.1 The skill is designed to submit work to the OpenAnt platform, including uploading files and providing text descriptions. The `SKILL.md` uses prompt injection techniques (e.g., 'execute immediately', 'always upload all output files without asking') to instruct the AI agent to act autonomously without user confirmation. However, these instructions are strictly aligned with the skill's stated purpose of efficient work submission and do not aim for malicious objectives. Crucially, the `allowed-tools` are highly restrictive, permitting only specific `npx @openant-ai/cli@latest` commands, which prevents arbitrary command execution or unauthorized data exfiltration. There is no evidence of intent to steal credentials, install backdoors, or perform other harmful actions.