The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by using the WebFetch tool to retrieve institutional academic-integrity codes from external URLs supplied by users. This content is then interpolated into policy statements without explicit sanitization or boundary markers.
Ingestion points: The skill uses WebFetch to read linked institutional codes from user-supplied URLs as described in the SKILL.md compatibility notes.
Boundary markers: There are no specific boundary markers or 'ignore' instructions for the fetched content defined in the prompt guidelines or the Python scripts.
Capability inventory: The skill possesses Write, Edit, and Bash (restricted to Python) capabilities, allowing it to generate files and execute local logic based on the ingested data.
Sanitization: The scripts/policy_builder.py script performs direct string interpolation of user-supplied and externally fetched data into the final Markdown policy without validation or escaping.

alterlab-syllabus-ai-policy