commit-security-scan
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill instructs the agent to execute shell commands (
git diff,git show,gh pr diff) to retrieve code changes. While these are essential for the skill's primary function, they involve interacting with the system's command line. - [PROMPT_INJECTION] (LOW): This skill is vulnerable to Indirect Prompt Injection (Category 8) as it ingests untrusted data from external sources (commits and pull requests).
- Ingestion points: Step 2 in
SKILL.mdidentifies that the agent reads output fromgh pr diffandgit diff, along with the full content of changed files. - Boundary markers: Absent. The instructions do not specify using delimiters or provide a system-level warning to the LLM to ignore instructions contained within the code diffs.
- Capability inventory: The skill can execute shell commands (
git,gh), write to the local file system (security-findings.json), and invoke other agent skills (threat-model-generation). - Sanitization: Absent. There is no mention of filtering or sanitizing the code content before it is processed by the LLM reasoning engine.
Audit Metadata