watchers
Poll RSS, JSON APIs, and GitHub with watermark dedup.
59
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./optional-skills/devops/watchers/SKILL.mdW011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime workflow polls outsider-authored external content (e.g., an RSS/Atom feed from a user-supplied URL, a GitHub repo’s issues/commits via GitHub API, or an arbitrary JSON endpoint), parses it into strings (title/body/summary) and prints them to stdout; the agent then reads that stdout and includes it in the LLM context for summarization.
- Repository
- NousResearch/hermes-agent
- Commit
145c713
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.