interview-master

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell scripts (analyze-commits.sh, extract-tech-stack.sh) and a Python script (calculate-impact.py) to execute git commands on local repositories. These tools are intended for generating repository statistics and project impact metrics as part of the skill's primary resume generation workflow.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes git commit messages and file contents which are potentially attacker-controlled.\n
  • Ingestion points: Git commit logs and repository files are analyzed by scripts in the scripts/ directory.\n
  • Boundary markers: The skill does not implement specific delimiters or warnings to ignore instructions embedded in commit messages.\n
  • Capability inventory: The skill utilizes subprocess execution (git) and file system access across all its analysis scripts.\n
  • Sanitization: No sanitization logic was identified for the content extracted from git history before it is passed to the agent for resume generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:14 PM