inkos-script-writing
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and reference files contain legitimate creative writing and adaptation guidelines. No malicious code, hardcoded credentials, or network exfiltration patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external, user-supplied content (novels, outlines) which creates a surface for indirect prompt injection. 1. Ingestion points: Untrusted source material provided by the user for adaptation as described in
SKILL.md. 2. Boundary markers: No delimiters or protective instructions are included to isolate user content from the agent's instructions. 3. Capability inventory: As noallowed-toolsare specified in the frontmatter, the agent retains access to all default tools, including shell and file system operations. 4. Sanitization: No input validation or filtering is performed on the ingested content.
Audit Metadata