critical-analysis-business-logic
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents which could contain malicious instructions.
- Ingestion points: The skill ingests
proposal draft,ToR,evidence register,work plan,team, andbudgetartefacts as described in the Inputs section ofSKILL.md. - Boundary markers: No explicit boundary markers or delimiters are defined to isolate untrusted data from the system prompt or skill instructions.
- Capability inventory: The skill is restricted to analysis and critique. It specifies a read-only default and does not include capabilities for network access, arbitrary command execution, or automated file writes outside the requested working copy.
- Sanitization: The instructions do not define any sanitization, filtering, or validation logic for the ingested external data.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not contain any executable scripts, binary files, or automated commands.
Audit Metadata