mockumentary-structure
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill defines a surface where untrusted user input is processed to create local filesystem outputs.\n
- Ingestion points: User-provided project details, outline requests, and pacing discussions (SKILL.md).\n
- Boundary markers: Absent; the skill does not define delimiters or provide instructions to ignore embedded commands within user content.\n
- Capability inventory: Writing content to
script/outline.mdandscript/treatment.md(SKILL.md).\n - Sanitization: Absent; no instructions are provided to the agent to sanitize or validate the user-provided data before writing to the files.
- NO_CODE (SAFE): No executable scripts or code blocks were found in the skill package.
Audit Metadata