meta-strategic-audit
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted external data, creating a surface for indirect prompt injection attacks.
- Ingestion points: The workflow in SKILL.md requires reading sensitive business artefacts including three years of financial results, management accounts, governance records, and interview notes from staff and outside parties.
- Boundary markers: There are no instructions defining the use of delimiters or specific warnings to ignore instructions embedded within the ingested documents or interview notes.
- Capability inventory: The skill is granted permission for analysis and drafting of findings, reports, and hand-off notes. While it specifies a read-only by default posture, the generated report content could be influenced by malicious instructions contained in the source documents.
- Sanitization: There is no evidence of sanitization, escaping, or filtering of external content before processing or interpolation into prompts.
Audit Metadata