← Back to Skills Marketplace
449
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install podcast-discovery
Description
Podcast discovery for Wherever.Audio -- find shows and episodes, generate wherever.audio links.
Usage Guidance
This skill appears coherent and limited to podcast discovery: it will call the public Clawsica API and fetch RSS feeds (network activity). It requires no secrets and has no install script, but includes a small Python utility you may need to run (pip install -r scripts/requirements.txt) if you want episode search locally. If you plan to enable web-search behavior implied by the docs, confirm which web/search tool the agent will use. As always, run included scripts in a controlled environment if you plan to execute them locally, and verify the Clawsica host (https://clawsica.wherever.audio) is trusted before relying on links returned by the skill.
Capability Analysis
Type: OpenClaw Skill
Name: podcast-discovery
Version: 0.0.4
The skill is classified as suspicious due to a potential Server-Side Request Forgery (SSRF) vulnerability in `scripts/search_feed_episodes.py`. The script uses `urllib.request.urlopen` to fetch RSS feeds from a URL provided as a command-line argument. While the `SKILL.md` explicitly instructs the AI agent to only use RSS URLs obtained from the trusted Clawsica service, a sophisticated prompt injection attack could potentially bypass this instruction, allowing an attacker to coerce the agent into fetching content from arbitrary internal or external URLs via the `rss-url` parameter, leading to SSRF. There is no evidence of intentional malicious behavior such as data exfiltration or backdoors.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and included scripts all focus on locating podcast RSS feeds, selecting episodes, and constructing wherever.audio links. No unrelated credentials, binaries, or config paths are required.
Instruction Scope
Runtime instructions direct the agent to query the public Clawsica endpoint and to fetch arbitrary RSS feed URLs (via the provided local script) — this is appropriate for the stated purpose. The SKILL.md also says to "search the web first" for discovery queries but does not prescribe a specific external search API; this is a minor vagueness (the agent may use its available web/search tool). The instructions explicitly forbid sending raw RSS XML to the model and limit token usage, which aligns with the token-budget policy.
Install Mechanism
There is no install spec (instruction-only), and included Python tooling has a small requirements.txt (feedparser, rapidfuzz, pytest). No downloads from untrusted URLs or archive extraction are present. Semantic rerank optionally imports heavy ML libs but those are not required and the code falls back safely if absent.
Credentials
The skill declares no required environment variables or credentials. All network calls are to public endpoints (Clawsica and arbitrary RSS URLs) appropriate to the skill's function. No secret exfiltration or unrelated credential access is requested.
Persistence & Privilege
The skill does not request permanent inclusion (always=false), does not modify other skills or global agent config, and does not require elevated system privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install podcast-discovery - After installation, invoke the skill by name or use
/podcast-discovery - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.4
- Major update: Migrated to a new implementation with a local feed tooling pipeline for episode lookup, to reduce token usage.
- Added local script (search_feed_episodes.py) for searching, filtering, and ranking podcast episodes from RSS feeds.
- New policies: "link-first" action policy (prioritizing link generation over metadata or further questions) and strict token budget for responses.
- Updated workflow and response guidelines to use local tools and compact outputs (no raw XML or large blobs).
- Added developer/testing instructions and requirements for running feed tooling locally.
- Clarified episode/show link construction, response format, and user query triggers.
v0.0.1
- Initial release of "clawpod", a podcast discovery skill for Wherever.Audio.
- Supports natural-language search for podcast shows and episodes, returning direct wherever.audio links.
- Classifies queries by intent and scope to tailor search (podcast show vs. episode).
- Integrates with Clawsica API for authoritative RSS feed discovery.
- Provides step-by-step workflow—search, RSS parsing, and link generation.
- Includes detailed usage instructions, privacy notes, and sample prompts.
Metadata
Frequently Asked Questions
What is Podcast Discovery?
Podcast discovery for Wherever.Audio -- find shows and episodes, generate wherever.audio links. It is an AI Agent Skill for Claude Code / OpenClaw, with 449 downloads so far.
How do I install Podcast Discovery?
Run "/install podcast-discovery" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Podcast Discovery free?
Yes, Podcast Discovery is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Podcast Discovery support?
Podcast Discovery is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Podcast Discovery?
It is built and maintained by aegrumet (@aegrumet); the current version is v0.0.4.
More Skills