semgrep-rule-variant-creator
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the 'semgrep' CLI to validate, test, and analyze rules.
- Evidence: Usage of
semgrep --validate,semgrep --test,semgrep --dump-ast, andsemgrep --dataflow-traceswithin Phase 3 and Phase 4 of the workflow. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes external Semgrep rule content provided by users.
- Ingestion points: The skill accepts an 'Existing Semgrep rule' as either a YAML file path or raw YAML content (SKILL.md).
- Boundary markers: The provided instructions do not specify any delimiters or warnings to ignore instructions embedded within the rule data.
- Capability inventory: The skill performs subprocess calls to the
semgrepbinary and writes rule/test files to the filesystem. - Sanitization: No evidence of sanitization or validation of the input rule content is provided in the skill instructions.
Audit Metadata