detailed-pr-description
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with the repository and GitHub. It specifically uses
gh pr viewandgh pr editto read and update Pull Request metadata, andgit statusto analyze the local environment. - [COMMAND_EXECUTION]: The skill identifies and runs validation commands or tests found within the project environment to assess test coverage (Workflow Step 4). This involves executing arbitrary shell commands defined in the analyzed repository.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from external sources that could contain malicious instructions.
- Ingestion points: The skill fetches data from Pull Request titles, descriptions, and changed source code (Workflow Step 1 and 2).
- Boundary markers: The instructions do not provide explicit delimiters or warnings to the agent to ignore instructions embedded within the PR content.
- Capability inventory: The agent has the capability to execute shell commands and mutate remote GitHub Pull Requests (Workflow Step 5).
- Sanitization: There is no evidence of sanitization or validation performed on the PR content before it is processed by the agent.
Audit Metadata