saas-poc-and-pilot-scoping
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential vector for indirect prompt injection.
- Ingestion points: The skill reads supplied tender, discovery, architecture, commercial, security, and operating evidence as stated in the 'Capability and Permission Boundaries' section of SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the agent when processing these external documents.
- Capability inventory: The skill is restricted to reading workspace files and drafting proposal artifacts. It does not have capabilities for network operations, command execution, or file system modifications outside the workspace.
- Sanitization: There is no evidence of content sanitization or validation for the ingested evidence.
- [SAFE]: The skill does not contain any executable code, obfuscated content, or persistence mechanisms. All external references target local files within a structured repository environment. The author attribution and contact information appear legitimate and consistent.
Audit Metadata