interview-loop-strategist
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data, such as project history and career narratives, to build preparation matrices and timelines using 'Write' and 'Edit' tools.
- Ingestion points: Project descriptions and career biography data in SKILL.md and referenced templates.
- Boundary markers: Absent; the skill lacks instructions for the agent to treat ingested career data as untrusted or to ignore instructions embedded within it.
- Capability inventory: The skill utilizes 'Read', 'Write', and 'Edit' tools to modify the environment based on user-supplied content.
- Sanitization: Absent; there are no validation or filtering mechanisms defined for the project descriptions before they are interpolated into the preparation strategy.
Audit Metadata