inkos-story-cover
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted user-supplied story details to drive a visual generation tool, creating a surface for indirect prompt injection.
- Ingestion points: Instructions in SKILL.md direct the agent to process "the actual work: title, genre, protagonist, central conflict" and convert a "manuscript" into a visual brief.
- Boundary markers: The instructions lack specific delimiters or warnings to treat ingested content as data rather than instructions, potentially allowing a malicious manuscript to influence the generation tool's behavior.
- Capability inventory: The skill uses the
generate_coverpath to execute image generation based on the processed story details. - Sanitization: There are no defined mechanisms to validate, sanitize, or filter the user-provided story content before interpolation into the visual brief.
Audit Metadata