checkpoint-read

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from Git commit messages which could be influenced by external contributors, potentially leading to the agent following embedded instructions.
  • Ingestion points: The skill reads commit history and details using git log and git show as described in SKILL.md.
  • Boundary markers: The instructions do not specify delimiters or guidelines to distinguish between commit message content and agent instructions during the analysis phase.
  • Capability inventory: The skill has the ability to execute shell commands (git).
  • Sanitization: There is no evidence of sanitization or filtering of the commit content before the agent summarizes it.
  • [COMMAND_EXECUTION]: The skill executes shell commands to interact with the local Git repository.
  • Evidence: The workflow in SKILL.md uses git log --oneline --decorate --grep '^checkpoint.*:' -n 25, git show --stat {SHA}, and git show {SHA} to retrieve data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 11:23 PM