The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bundled Node.js script (scripts/inventory-data-model.mjs) to automate the analysis of the project's data architecture and database schemas.
[DATA_EXFILTRATION]: The provided inventory script performs sensitive file access by scanning the project's source code for patterns matching personal data (PII) and credentials, including API keys, tokens, and passwords. This exposure of unhashed secrets is intended to facilitate the audit but involves scanning high-value sensitive targets.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze potentially untrusted external data from product notices and marketing copy to verify checkable claims.
Ingestion points: Product notice text, settings screens, and marketing copy provided by the analyzed project.
Boundary markers: No specific delimiters or safety warnings are implemented to differentiate these external inputs from system instructions.
Capability inventory: The skill possesses file read access via the inventory script and the authority to modify UI components and privacy notice text.
Sanitization: There is no evidence of sanitization or filtering applied to the ingested external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references numerous official regulatory and standards organizations for legal research, including government domains such as ftc.gov, ico.org.uk, and europa.eu. These references are to well-known and trusted official sources.

data-rights