think-scamper
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of markdown instructions, templates, evaluation cases, and metadata. It does not contain any scripts, binaries, or shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied 'seed ideas' as input for transformation. This represents an attack surface for indirect prompt injection where malicious instructions could be embedded in the input data.
- Ingestion points: User-provided seed ideas are ingested as the primary subject for the SCAMPER transformation in SKILL.md.
- Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the user-provided seed.
- Capability inventory: The skill does not possess any dangerous capabilities such as network access, file system writing, or code execution across its files.
- Sanitization: There is no mention of sanitizing or escaping the user-provided seed before processing.
Audit Metadata