clawdbot-monitor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill uses
WebFetchto retrieve documentation and repository structure fromgithub.com/clawdbot/clawdbot. This is a known public source and the usage is consistent with the stated purpose of the skill. - [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from an external repository and processes it.
- Ingestion points: Files fetched from
github.com/clawdbot/clawdbot(README.md, CLAUDE.md, releases, etc.) viaWebFetch. - Boundary markers: Absent; there are no instructions to the agent to treat external content as untrusted or to use delimiters.
- Capability inventory: The agent has access to
WebFetch,Read,Grep, andGlob, allowing it to read both web content and local configuration files like.claude-plugin/plugin.json. - Sanitization: Absent; the fetched content is analyzed directly for pattern matching and comparison.
Audit Metadata