The Agent Skills Directory

[SAFE]: The skill uses a standard and secure implementation for interacting with its backend service. Authentication credentials are retrieved from environment variables rather than being hardcoded, and network communication is restricted to the vendor's official domain.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and summarize untrusted external data.
Ingestion points: External content is ingested via materialUrl (remote URLs), materialFile (uploaded documents), and materialText (user-pasted text) as defined in SKILL.md and references/form-schema.json.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external content as untrusted or to ignore embedded instructions.
Capability inventory: The skill's runtime capabilities are limited to making HTTP POST requests to the ai-skills.ai API via scripts/run.py to process the data.
Sanitization: The provided scripts do not perform validation or sanitization of the content retrieved from external sources before it is processed.

ai-market-research