oc-pr
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data from GitHub Pull Requests, including file changes, PR descriptions, and discussion comments. This data could contain malicious instructions aimed at influencing the agent's evaluation or merging logic.\n
- Ingestion points: PR metadata, file content, and discussion threads accessed via GitHub API as described in SKILL.md.\n
- Boundary markers: The instructions do not define explicit boundary markers or ignore-rules for the data ingested from PRs.\n
- Capability inventory: The skill possesses the capability to execute shell commands (
git merge,git push,gh pr) that modify the state of the repository.\n - Sanitization: There are no requirements for sanitizing or escaping the data read from external PR sources before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill uses local command-line tools such as
gitandghto perform repository management tasks. These include fetching PR data, creating local integration branches, performing merges, and pushing to the development branch. These actions are aligned with the skill's primary purpose and are mitigated by required user confirmations.
Audit Metadata