pr-pilot
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute Git and GitHub CLI (
gh) commands for branch management, PR creation, rebasing, and merging. These operations are core to the skill's stated purpose. - [PROMPT_INJECTION]: The skill is potentially vulnerable to indirect prompt injection because it ingests external data from PR comments and CI logs through the
/pr-review-fixerskill. A malicious actor could provide instructions within a PR comment that the agent might inadvertently follow. - Ingestion points: PR comments and CI logs fetched via
ghand processed by the/pr-review-fixerskill. - Boundary markers: Absent. The workflow does not explicitly delimit untrusted input from instructions.
- Capability inventory: The skill has access to
Bash,Write, andEdittools, allowing it to modify the filesystem and execute shell commands. - Sanitization: None detected. The skill relies on the underlying LLM's safety filters when processing the external data.
Audit Metadata