fsi-pe-deal-screening
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external materials (CIMs, teasers, and broker materials) provided by users. 1. Ingestion points: Financial documents and deal materials specified in SKILL.md. 2. Boundary markers: Absent; there are no specific instructions or delimiters used to isolate the ingested data from the agent's core instructions. 3. Capability inventory: Data extraction, comparison against criteria, and memo generation; no high-risk command execution or network capabilities were identified in the skill. 4. Sanitization: Absent; no content validation or filtering is specified for the inbound deal materials.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata without any accompanying executable scripts, binaries, or external code dependencies.
Audit Metadata