ask-me
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources and user responses to construct a decision tree, creating a potential attack surface. * Ingestion points: Fetches environmental facts from the file system and tools as mentioned in SKILL.md. * Boundary markers: Absent; there are no instructions to delimit or ignore instructions within the retrieved facts. * Capability inventory: Includes file system access and general tool usage for fact-gathering. * Sanitization: Absent; the skill does not specify any validation or filtering of external data before integration into the session context.
Audit Metadata