melech-foresee
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a 'locked plan' to generate the visualization. This creates a surface where instructions or malicious content in the plan could attempt to influence the agent's output or inject content into the HTML file.\n
- Ingestion points: Planning documents or conversation context (SKILL.md instructions to 'Read the locked decisions').\n
- Boundary markers: Absent from the input processing instructions.\n
- Capability inventory: File writing and browser invocation (SKILL.md instructions to write the HTML file and 'Open the file in the browser').\n
- Sanitization: The template.html file includes basic HTML entity encoding (replacing '<' and '&') for the diff line content to mitigate basic script injection.\n- [DYNAMIC_EXECUTION]: The skill generates an HTML file containing JavaScript and instructs the agent to open it in a browser. This behavior is the primary intended purpose of the skill and is performed using a predefined local template.
Audit Metadata