implement-pr
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub issues which could contain malicious instructions.
- Ingestion points: Uses
gh issue viewto read issue titles, bodies, and comments inSKILL.md. - Boundary markers: There are no explicit delimiters or warnings to the agent to ignore instructions embedded within the issue data.
- Capability inventory: The agent has the ability to execute shell commands (
git,gh), and repository-specific test, lint, and build scripts as described inSKILL.md. - Sanitization: No sanitization or filtering of the issue content is performed before it is used to plan tasks.
- [COMMAND_EXECUTION]: The skill is instructed to execute arbitrary build, test, and lint commands defined by the repository it is working on. While necessary for its function, this poses a risk if the repository contains malicious scripts or if an attacker can influence the commands through indirect prompt injection.
Audit Metadata