commit-archaeologist

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches skill components from the author's repository during installation as described in the README.
  • [COMMAND_EXECUTION]: Executes local git commands through a Python script. The implementation uses list-based arguments for subprocess.run to prevent shell injection and includes path validation to ensure operations are confined to the repository using os.path.commonpath to mitigate path traversal risks.
  • [INDIRECT_PROMPT_INJECTION]: Processes untrusted data from git commit messages. An attacker could embed malicious instructions in the history. The skill mitigates this through explicit evidence rules and interpretation guidelines that instruct the agent to maintain low confidence in inferred intent.
  • Ingestion points: Commit subjects and bodies are read in scripts/archaeologist.py via git log and git show commands.
  • Boundary markers: Guidance in SKILL.md and references/reading-git-history.md helps the agent process data safely by labeling conclusions as inferences.
  • Capability inventory: Limited to read-only local git command execution with no file-write or network capabilities.
  • Sanitization: Commit messages are returned in a structured JSON format without specific sanitization of the message text content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 08:49 PM