story-sense
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies story states and recommends interventions based on user-provided descriptions of story problems. This input serves as a potential vector for indirect prompt injection.
- Ingestion points: User story descriptions and responses to diagnostic questions described in
SKILL.md. - Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the skill instructions.
- Capability inventory: The skill executes local Deno scripts (
entropy.ts,functions.ts) with broad read permissions (--allow-read) as specified in the script documentation. - Sanitization: No input sanitization or verification is performed on the data being diagnosed.
- [COMMAND_EXECUTION]: The skill utilizes Deno to run local scripts with file system access. The
entropy.tsscript provides a--fileargument which can be used to load external JSON data. This feature could be abused to read sensitive local files if they are in JSON format and the agent is manipulated into accessing specific paths.
Audit Metadata