interview-evaluation

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted interview data from pasted text or local files, which introduces a risk of indirect prompt injection where instructions hidden in the transcripts could influence agent behavior.
  • Ingestion points: Untrusted data enters the context via dialogue records pasted into chat or read from local file paths provided by the user (SKILL.md).
  • Boundary markers: The prompt does not define specific delimiters or instructions to ignore embedded commands within the interview content.
  • Capability inventory: The skill utilizes file reading and optional file writing capabilities to process and archive summaries (SKILL.md).
  • Sanitization: There is no mention of filtering, escaping, or validating the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 08:32 AM