02-executive-summary
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is instructional and does not contain any executable scripts, remote code downloads, or commands that access sensitive credentials.
- [PROMPT_INJECTION]: The skill processes external, untrusted documentation such as RFPs, ToRs, and assignment briefs. This constitutes a surface for indirect prompt injection, which is a primary functional requirement of the skill and is handled by the agent's inherent safety guardrails.
- Ingestion points: ToR, RFP, advert, and assignment briefs (SKILL.md)
- Boundary markers: Not explicitly defined in the template
- Capability inventory: Read and search access only
- Sanitization: No explicit content filtering mentioned
Audit Metadata