summarize-interview
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted interview transcript data, which creates a potential surface for indirect prompt injection.
- Ingestion points: As per the 'Context' section in SKILL.md, the skill reads content from attached files (text, PDF, audio transcription) or text pasted directly by the user.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the input transcript content.
- Capability inventory: The skill is instructed to write and save markdown documents into the user's workspace, representing a file-write capability.
- Sanitization: The skill does not specify any sanitization, validation, or filtering of the input transcript data before it is summarized.
Audit Metadata