skills/security-phoenix-demo/security-skills-claude-code/opengrep-rule-generator/Gen Agent Trust Hub
opengrep-rule-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches vulnerability definitions and security documentation from well-known and authoritative sources, including Mitre's CWE database (cwe.mitre.org) and the OWASP Foundation website (owasp.org), to ensure generated rules are accurate and aligned with industry standards.- [COMMAND_EXECUTION]: The skill instructs the agent to validate generated rules using the
opengrep scancommand, which is the intended and primary functionality of this security assistant.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external content and user-provided code to generate rules. - Ingestion points: User-supplied code and vulnerability descriptions, as well as external content fetched from mitre.org and owasp.org via WebFetch.
- Boundary markers: The instructions do not specify the use of delimiters to separate untrusted data from the agent's instructions.
- Capability inventory: The skill is capable of network operations (searching and fetching) and file operations (writing rule files).
- Sanitization: No specific sanitization or validation logic is defined for the ingested data. This exposure is considered acceptable within the context of the skill's primary purpose as a security research and auditing tool.
Audit Metadata