academic-letter-architect
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, specifically candidate CVs, resumes, and personal statements, to inform the recommendation letter drafting process.
- Ingestion points: Untrusted data enters the agent context through the context-gathering phase described in SKILL.md and resources/methodology.md.
- Boundary markers: The instructions do not define clear delimiters or 'ignore embedded instructions' warnings for the agent when processing these external documents.
- Capability inventory: The skill's primary capability is text generation and analysis, which could be influenced by malicious instructions embedded in the source data.
- Sanitization: There are no explicit requirements for sanitizing or validating the content of the external candidate documents before they are used in the prompt interpolation process.
Audit Metadata