The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). • Ingestion points: User-supplied 'Industry', 'Entity type', and 'Target name' inputs are gathered in Step 1 and used to generate the 10-vector pressure map and storyboard. • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing logic to isolate untrusted data from the prompt instructions. • Capability inventory: The skill produces text-based analysis and does not invoke subprocesses, file-system writes, or network-request tools. • Sanitization: No input validation, escaping, or filtering of external content is implemented to prevent the execution of embedded instructions.

moatmri