sast-semgrep
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes
semgrepcommands via the shell. This is necessary for operation but introduces a risk of shell injection if the<target-path>variable is manipulated with malicious characters. - [EXTERNAL_DOWNLOADS] (LOW): The skill requires the
semgrepPython package. The installation of external packages not included in the trusted source list is normally a MEDIUM finding, but is downgraded here because it is the primary purpose of the skill. - [PROMPT_INJECTION] (LOW): The skill parses and summarizes output from scanned codebases, which creates a surface for indirect prompt injection if the scanned code contains malicious instructions intended to mislead the security agent.
- Ingestion points: Code files located at the user-specified
<target-path>. - Boundary markers: None specified to distinguish untrusted code results from agent instructions.
- Capability inventory: Shell execution (
semgrep scan) and file system access for results. - Sanitization: No sanitization is performed on scan results before they are summarized by the agent.
Audit Metadata