apply-program-theme-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a legitimate academic research workflow. No evidence of credential theft, malicious command execution, persistence, or obfuscation was found in the instructions. The workflow emphasizes using official sources and provides clear criteria for differentiating between declared and inferred information.
- [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface as it fetches external data from web search results (SKILL.md, Workflow Step 2). 1. Ingestion points: Fetched program pages, call documents, and curriculum lists. 2. Boundary markers: Not explicitly defined for the fetched content. 3. Capability inventory: The skill uses web search and text processing; it does not possess capabilities for file writing, network exfiltration of sensitive files, or arbitrary code execution. 4. Sanitization: Relies on verbatim extraction and logical decomposition of sources, which acts as an inherent check on data integrity.
Audit Metadata