The Agent Skills Directory

[SAFE]: The skill provides legitimate documentation and code examples for the data.gouv.fr platform. No malicious instructions, obfuscation, or persistence mechanisms were detected.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external APIs which constitutes a theoretical attack surface for indirect prompt injection.
Ingestion points: API responses from data.gouv.fr, metric-api.data.gouv.fr, and tabular-api.data.gouv.fr in JSON and CSV formats.
Boundary markers: Not present; the documentation does not specify delimiters to isolate external data from agent instructions.
Capability inventory: The skill allows the agent to perform network requests (GET/POST/PUT/PATCH/DELETE) and process datasets, which are standard operations for an API reference skill.
Sanitization: No specific sanitization or filtering logic is described; the skill relies on the agent's native handling of external data.
[CREDENTIALS_UNSAFE]: The skill correctly handles the security of credentials by instructing the agent to never log or echo the X-API-KEY and to only perform write operations with explicit user intent.

datagouv-apis