The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional content, documentation, and reference materials. It does not contain executable code, scripts, or automation that performs actions outside of searching for text patterns in a local environment using tools like ripgrep. All references to external libraries are for identification purposes during audits and do not represent dependencies of the skill itself.
[INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by instructing the agent to ingest and analyze untrusted source code and configuration files. This behavior is inherent to its primary function as a security auditing tool and is not malicious in nature.
Ingestion points: Source code and configuration files (Keycloak, Auth0, Okta, SAML metadata) detected in the target repository being audited.
Boundary markers: None explicitly provided in the audit instructions.
Capability inventory: File reading and pattern matching using ripgrep to trace data flows and identify authentication flaws.
Sanitization: Not applicable as the skill focuses on static code analysis rather than runtime processing of data for execution.

aegis-oauth-sso