case-study-writer
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process external data such as customer transcripts and evidence, which creates a surface for indirect prompt injection.\n
- Ingestion points: Customer context, interview transcripts, and business outcome data are identified as inputs in
SKILL.mdandmeta/skill.json.\n - Boundary markers: The skill does not define explicit delimiters or instructions to ignore commands embedded within the input data.\n
- Capability inventory: The skill has no capabilities or tools for file system access, network operations, or shell command execution.\n
- Sanitization: No specific sanitization or filtering logic is described for the input data before it is processed by the agent.\n- [NO_CODE]: The skill consists entirely of markdown instructions, output examples, and JSON metadata, with no attached scripts, binaries, or automated installation processes.
Audit Metadata