The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for using standard security tools such as openssl, sslyze, and testssl.sh to perform network-based security audits. These commands are typical for the skill's stated purpose of auditing cryptographic configurations.
[EXTERNAL_DOWNLOADS]: The skill suggests the installation of standard Python libraries (cryptography, requests, pyOpenSSL) from official registries. It also references well-known security resources from NIST, Mozilla, and OWASP to guide the user's assessments.
[DATA_EXFILTRATION]: The included tls_auditor.py script performs network connections to hostnames and ports provided by the user. These operations are limited to the intended purpose of auditing TLS configurations and do not involve unauthorized access to sensitive local data or exfiltration to external servers.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes untrusted data from network responses, such as SSL certificates and HTTP headers. The tls_auditor.py script manages this data by outputting structured JSON, which helps maintain boundaries between the data and the agent's instructions.
[SAFE]: The use of ssl._create_unverified_context() and ssl.CERT_NONE within the auditing script is a functional necessity for analyzing servers that have invalid or expired certificates. This is a standard practice for security auditing tools to diagnose configuration failures.

13-crypto-analysis