The Agent Skills Directory

[SAFE]: The skill communicates with its official backend at ai-skills.ai using a standard Python runner script. No unauthorized network operations or communication with suspicious domains were detected.
[SAFE]: Secret management is handled correctly by requiring the AISKILLS_API_KEY to be provided via environment variables, rather than being hardcoded in the skill files.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill is designed to ingest and analyze untrusted data provided via URLs, file uploads, and text snippets.
Ingestion points: materialUrl, materialFile, and materialText parameters defined in references/form-schema.json.
Boundary markers: None identified in the provided skill instructions or schema.
Capability inventory: The skill performs network requests to the AI Skills API via scripts/run.py.
Sanitization: No client-side input validation or escaping is present in the runner script.

copywriting