hr-round

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of interview answers and stores them in a permanent file ($CRACKED_DIR/stories.md) to build a 'story bank'. This content is later read back into the agent's context and shared with other skills.
  • Ingestion points: User answers provided during the interview training loop are processed, rewritten, and stored in a Markdown file.
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands when reading from or writing to the story bank file.
  • Capability inventory: The skill possesses capabilities to read and write files on the local system and can invoke other internal skills (e.g., 'cracked-profile', 'company-intel').
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the user-provided content before it is incorporated into the story bank or re-loaded into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 06:30 AM