skills/pipecat-ai/pipecat/pr-submit/Gen Agent Trust Hub

pr-submit

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands (status, diff, log, push) and gh (GitHub CLI) to manage repository state and submit pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's diffs and commit history during the commit and review process.
  • Ingestion points: Git diff outputs, file contents, and commit messages are read by the agent to determine commit structure and branch names.
  • Boundary markers: No explicit delimiters or instructions are used to separate repository content from the skill's operational instructions.
  • Capability inventory: The skill has the ability to commit changes, create new branches, and push code to remote repositories.
  • Sanitization: No evidence of sanitization or filtering for the processed repository data is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 08:47 PM