dbk-pr-execute-reply
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gitand the GitHub CLI (gh) to perform file modifications, stage changes (git add -p), create commits, push to remote branches, and interact with the GitHub API. These commands are fundamental to the skill's purpose but involve high-privilege access to the user's codebase and GitHub account. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub PR comments using
gh api repos/{owner}/{repo}/pulls/{pr_number}/comments. This constitutes a vulnerability surface where malicious instructions embedded in a PR review could potentially influence the agent's behavior during the 'Locking the Plan' or 'Execution' phases. - Ingestion points: External PR comments are fetched and parsed from the GitHub API in
SKILL.md(Workflow Step 6). - Boundary markers: There are no explicit delimiters or specific warnings provided to the agent to treat fetched comment text as untrusted data.
- Capability inventory: The skill has the capability to write to the local filesystem, commit code, push to remote repositories, and make authenticated API calls to GitHub (commenting and requesting reviewers).
- Sanitization: No explicit sanitization or filtering is performed on the content of the comments before they are used to determine execution steps or generated replies.
Audit Metadata