signals-scout-skills-store
Skill-hygiene scout for the team's PostHog skills store, read entirely via the MCP skill tools. Watches recently-changed skills — plus a slow rotation over the most-used, highest-leverage ones — for statically-verifiable authoring violations: vague descriptions, bloated bodies, dead bundled-file links, kitchen-sink scope, committed secrets. Files each non-compliant skill as a report in the inbox, with the copy-ready fix inside.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: 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
SKILL.md describes using MCP tools to fetch and scan other stored skills’ bodies and bundled files (“skill-get” and “skill-file-get”), which are outsider-authored free-text instructions/data not written by the operating user, and that fetched text is ingested into the agent’s LLM context for the checklist and secret/disclosure scans.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly instructs the agent to fetch and refresh its ruleset from live sources at runtime (e.g. https://agentskills.io/specification, https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices, https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md), which are runtime external fetches that directly influence the agent's checklist and behavior.
- Repository
- PostHog/posthog
- Commit
5b94e47
- 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.