story-sense
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified.
- Ingestion points: The skill processes user-provided story descriptions and 'symptoms' provided during the agent's diagnostic conversation as described in SKILL.md.
- Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are present when the agent handles the writer's input.
- Capability inventory: The skill executes local Deno scripts (entropy.ts, functions.ts) and writes persistent diagnostic output to the project's filesystem.
- Sanitization: No explicit sanitization or validation of user-provided narratives is implemented before the data is processed for diagnosis or file writing.
- [COMMAND_EXECUTION]: The skill utilizes local Deno scripts to provide creative randomization and role generation. As documented in SKILL.md, the agent is instructed to execute 'scripts/entropy.ts' and 'scripts/functions.ts' using the 'deno run' command with read permissions to access local data files.
Audit Metadata