The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill requires a wallet private key to be provided in the FITTINGS_PRIVATE_KEY environment variable for transaction signing. While the documentation recommends using a throwaway wallet, this practice exposes the secret to the local environment.
[EXTERNAL_DOWNLOADS]: The skill documentation suggests using curl to download the call.mjs helper script directly from the vendor's domain (https://fittings.sh/skill/call.mjs) if it is missing from the skill package.
[PROMPT_INJECTION]: The skill fetches content from user-provided URLs and injects it into the agent's context, creating an indirect prompt injection vector.
Ingestion points: Untrusted content is ingested via the url parameter of the doc.url-to-markdown endpoint.
Boundary markers: No explicit markers or instructions are provided to the agent to distinguish the fetched content from its own system instructions.
Capability inventory: The script call.mjs possesses network access and cryptographic signing capabilities.
Sanitization: The service converts HTML to Markdown but does not appear to filter or sanitize the resulting text for malicious instructions.

doc-url-to-markdown