comic-writer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting untrusted user data, such as story premises and character descriptions, and interpolating this information into complex script templates.
- Ingestion points: Data enters the agent context through user responses to queries about format, genre, and premise, as described in Step 1 of
SKILL.md. - Boundary markers: There are no defined boundary markers or specific instructions to help the agent distinguish between user-provided story content and potentially malicious instructions embedded within that content.
- Capability inventory: The skill possesses the capability to write Markdown files to the local file system using variable naming patterns, as specified in the Output Format section of
SKILL.md. - Sanitization: The instructions lack any sanitization or validation steps to filter or escape user-supplied text before it is processed for script generation.
Audit Metadata