recoup-internal-consulting-sow-generator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from "proposal/discovery" documents to generate contractual output, creating a vulnerability to indirect instructions.
- Ingestion points: The workflow in
SKILL.md(Step 1) pulls scope information from discovery and proposal files. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard malicious prompts embedded within the ingested proposal data.
- Capability inventory: The skill has the ability to write files to the
clients/directory and can pass data to the sibling skillrecoup-internal-consulting-tasteful-design. - Sanitization: The instructions do not define any sanitization, validation, or filtering for the external content before it is used to draft the SOW.
Audit Metadata