campfire
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from multiple sources without sanitization.\n
- Ingestion points:
SKILL.md(Step 2 in 'Before You Begin' scans names and descriptions of installed skills; Step 4 checks recent activity in calendar, project management, and messaging tools).\n - Boundary markers: Absent. The skill does not define delimiters to separate external tool outputs from the agent's internal instructions.\n
- Capability inventory: The skill uses the retrieved data to generate character dialogue and 'campfire' interactions across the session.\n
- Sanitization: Absent. There is no validation or filtering of the content retrieved from external tools or skill metadata before it is used to influence the agent's output.
Audit Metadata