navvy
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands using
git,sort,uniq,grep, andheadto extract metrics from the local repository history. These commands are static and do not take user-supplied arguments that could lead to command injection. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit logs (messages, filenames, and author names) and provides them to the agent for synthesis.
- Ingestion points: Git commit history (messages, filenames, author names) read via
git logandgit shortloginSKILL.md. - Boundary markers: Absent. The commands output raw text which is then processed by the agent.
- Capability inventory: None. The skill's scripts only perform read operations and do not have write, network, or execution capabilities beyond the initial diagnostic commands.
- Sanitization: Absent. The agent receives the raw output of the git commands.
Audit Metadata