skills/security-phoenix-demo/security-skills-claude-code/opengrep-rule-generator-research/Gen Agent Trust Hub
opengrep-rule-generator-research
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web search results (CVE details, exploit examples) and user-provided code snippets to generate rule files.\n
- Ingestion points:
SKILL.md(Vulnerability Research Plan) specifies retrieving data usingWebSearchandWebFetchtools from external URLs like MITRE and OWASP databases.\n - Boundary markers: The instructions do not specify the use of delimiters to isolate untrusted external content from the skill's instructions, nor does it provide warnings for the agent to ignore embedded instructions within that content.\n
- Capability inventory: The skill is designed to write rule files and test files to the local file system and can invoke the
opengreptool for validation purposes.\n - Sanitization: There is no evidence of sanitization or validation of the content retrieved from external sources before it is processed by the agent to construct rules.
Audit Metadata