semgrep-rule-creator
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and rule syntax guides from semgrep.dev and its official GitHub repository. These are well-known services and trusted repositories.
- [COMMAND_EXECUTION]: The skill uses Bash to execute semgrep commands, such as --test, --validate, and --dump-ast. This execution is confined to the skill's primary purpose of developing and verifying static analysis rules.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8). Ingestion points: Documentation links retrieved via WebFetch in SKILL.md. Boundary markers: No explicit delimiters are used to isolate fetched external content from the agent's internal instruction set. Capability inventory: The skill utilizes Bash for command execution, alongside Write and Edit tools for file manipulation. Sanitization: There is no mechanism described to filter or validate the content retrieved from external URLs before processing.
Audit Metadata