roof-qualification-check
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted contractor bid and RFP data to evaluate qualification gates and assign sub-scores, which creates a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context from
rfp.mandatory_requirements, the bid'squalificationsdata, andrfp.submission_requirements(SKILL.md). - Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions embedded within the processed contractor documents.
- Capability inventory: The skill is authorized to write to the filesystem at
<rfp-dir>/roof-review-output/manifests/bid_<slug>.qual.json(SKILL.md). - Sanitization: Absent. There is no evidence of filtering or validation of the untrusted text before it is processed by the agent's logic.
Audit Metadata