triage
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external platforms (GitHub and Discord) which could contain malicious instructions designed to manipulate the agent's reasoning or reporting.
- Ingestion points: The skill reads external activity logs from
/memory/github/prs.md,/memory/github/issues.md, and/memory/discord/YYYY-MM-DD.md. - Boundary markers: No explicit instructions are provided to the agent to ignore or treat embedded instructions within these data sources as untrusted text.
- Capability inventory: The skill utilizes
memory-readto ingest data,memory-writeto update status files, and provides summaries to the chat interface. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from GitHub or Discord before it is processed by the LLM.
Audit Metadata