developer-advocate
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and respond to content from untrusted external sources, which creates a potential surface for instructions embedded in community data.\n
- Ingestion points: External platforms including GitHub issues, Stack Overflow questions, and Discord/Slack threads as specified in the 'Workflow Process' and 'Community Building' sections.\n
- Boundary markers: The instructions lack specific delimiters or guidelines for the agent to distinguish between its internal instructions and potentially malicious commands embedded in external developer content.\n
- Capability inventory: The skill is composed entirely of markdown instructions and templates; it does not request tool access, define scripts, or initiate autonomous network or file system operations.\n
- Sanitization: There are no instructions provided for the validation or sanitization of data retrieved from the community platforms.
Audit Metadata