semgrep-rule-variant-creator

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from an existing Semgrep rule file and uses that content to generate new rule and test files. This creates a surface where a malicious rule file could attempt to influence the agent's behavior via embedded instructions.
  • Ingestion points: The agent reads the file specified by rulePath in SKILL.md to perform translation and applicability analysis.
  • Boundary markers: The skill does not explicitly define boundary markers or instruct the agent to disregard potential instructions contained within the ingested rule file.
  • Capability inventory: The agent has significant capabilities including file system access (Read, Write, Edit, Glob), shell execution (Bash), and orchestration via the Workflow tool.
  • Sanitization: No sanitization or validation of the input rule's content is described before it is processed by the agent's reasoning engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:58 AM
Security Audit — agent-trust-hub — semgrep-rule-variant-creator