business-rule-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process legacy source code, production logs, and data (Workflow steps 1, 4, and 6), which are untrusted ingestion points. While this creates a surface for indirect prompt injection via malicious code comments or log data, the skill provides no active capabilities that could be exploited.
- Ingestion points: Source code, legacy logic, production logs, and production data referenced in SKILL.md.
- Boundary markers: None specified in the instructions.
- Capability inventory: No tools, scripts, or executable commands are defined or provided in the skill.
- Sanitization: No sanitization or filtering of external content is mentioned.
- [NO_CODE]: The skill consists entirely of markdown documentation and YAML frontmatter. It does not include any scripts, executables, or tool definitions that perform actions on the system.
Audit Metadata