syllabus-intake-parser
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs data extraction from external academic documents, which represents an inherent surface for indirect prompt injection should those documents contain malicious instructions.\n
- Ingestion points: Academic documents such as RPS, RPP, and modules (SKILL.md).\n
- Boundary markers: None explicitly defined in the documentation.\n
- Capability inventory: Structured data extraction and temporal mapping.\n
- Sanitization: The skill instructs the agent to mask sensitive identifiers (NIDN/NIK) but does not provide specific sanitization for natural language instructions within the input documents.\n- [NO_CODE]: The analysis of the skill reveals only instructional documentation and structural templates in SKILL.md, with no associated scripts, binaries, or executable code, minimizing direct technical risks.
Audit Metadata