summarize-interview
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (interview transcripts) and has the capability to write files, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Processes transcripts provided by the user via file attachments (text, PDF, audio) or direct text input as described in SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings to isolate the transcript content from the agent's instructions.
- Capability inventory: The skill is explicitly instructed to save a markdown document to the user's workspace, which could be exploited if malicious instructions are hidden in the transcript.
- Sanitization: There is no evidence of content sanitization, validation, or filtering of the external transcript data before it is processed or written to a file.
Audit Metadata