founder-comp-playbook
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses templates such as
templates/founder-offer-walkthrough.mdandtemplates/founder-counter-offer.mdto generate deliverables based on user-supplied information. This creates a surface where malicious instructions could be embedded in the input data. - Ingestion points: User-provided fields for company name, owner, candidate name, and specific compensation package details in the provided templates.
- Boundary markers: The templates do not utilize explicit delimiters or instructions to ignore potentially malicious embedded content.
- Capability inventory: The skill includes a local utility script
scripts/check-output.pywhich performs read-only regex validation on content. It does not have file-write, network, or dynamic execution capabilities. - Sanitization: There is no evidence of input sanitization or filtering for the data interpolated into the templates.
Audit Metadata