The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard shell utilities such as curl, grep, and tee to retrieve and analyze HTTP response headers. These operations are restricted to the intended purpose of auditing web security configuration.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to target URLs provided by the user to inspect their headers. It also provides a reference link to the well-known security analysis service securityheaders.com for further documentation.
[DATA_EXFILTRATION]: No evidence was found of unauthorized data transmission or access to sensitive local files such as credentials, environment variables, or SSH keys. Network activity is limited to checking the target server's headers.
[PROMPT_INJECTION]: The skill ingests data from external servers via HTTP headers, which represents a potential surface for indirect prompt injection. However, since the data is processed using non-LLM shell utilities for analysis, the risk to the agent's logic is minimal.
Ingestion points: External data is fetched from remote servers via curl and stored in /tmp/headers_raw.txt.
Boundary markers: None present; the raw header content is processed directly.
Capability inventory: The skill possesses network access (curl) and local file system write access (/tmp).
Sanitization: No explicit sanitization is performed on the header values before they are printed to the console.

security-headers