bug-bash-facilitator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve the agent processing untrusted feedback from session participants, creating an attack surface for indirect prompt injection.
- Ingestion points: The shared backlog board in Step 3 and the async logs in Step 6 where participants enter free-text bug reports.
- Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions when reading participant-logged data.
- Capability inventory: The agent, acting as facilitator, is tasked with real-time triage, assigning owners, and generating a post-bash debrief based on the collected entries.
- Sanitization: Absent; the skill does not specify any validation or sanitization of the participant-supplied text.
Audit Metadata