The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides shell commands and bash script examples for interacting with the AccessHawk REST API and managing the skill environment. Evidence includes examples using curl, jq, and the npx skills add command.\n- [EXTERNAL_DOWNLOADS]: The skill communicates with the accesshawk.ai domain to perform accessibility scans and retrieve reports. This is the official service domain and the interaction is necessary for the skill's primary function.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes content from third-party websites by performing accessibility audits and presenting the findings to the agent. This represents an attack surface where malicious external content could influence agent behavior.\n
Ingestion points: Data returned from the GET /api/v1/scans/{jobId} endpoint contains descriptions and recommendations derived from external URLs provided by the user.\n
Boundary markers: The instructions do not recommend specific delimiters or instruction-ignore blocks to isolate the external API response from the agent's system instructions.\n
Capability inventory: The skill utilizes shell command execution via curl and jq for API interaction.\n
Sanitization: The skill does not specify any validation, escaping, or sanitization of the issue data received from the remote API before processing.

accesshawk