pr-draft-summary

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • System Command Execution: The skill utilizes various git commands, including git diff, git log, and git ls-files, to retrieve branch information and file changes. These operations are essential for generating accurate summaries but involve the execution of shell commands to inspect the local environment.
  • Indirect Prompt Injection Surface: The skill is designed to ingest and summarize data from git commit logs and file diffs. This creates a surface where instructions embedded in commit messages or code comments could potentially influence the agent's summary output.
  • Ingestion points: Data is collected from git log --oneline, git diff, and the list of untracked files.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" rules to distinguish between repository metadata and potential instructions within that metadata.
  • Capability inventory: The agent has the capability to execute shell commands (git) and generate text blocks for the user.
  • Sanitization: No explicit sanitization or filtering logic is specified for the data retrieved from the repository before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:08 AM
Security Audit — agent-trust-hub — pr-draft-summary