inkos-imitation-writing
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for creative writing tasks. It contains no scripts, binaries, or shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided reference texts to extract stylistic methods. While this constitutes an input surface for indirect prompt injection, the skill lacks any dangerous capabilities (such as network access, file system writes, or command execution) that could be exploited if malicious instructions were embedded in the reference text.
- Ingestion points: Reference text supplied by the user as described in SKILL.md.
- Boundary markers: None defined.
- Capability inventory: No tools or commands for network, file, or system access are present in the skill.
- Sanitization: No sanitization logic is present.
Audit Metadata