The Agent Skills Directory

[SAFE]: The skill provides security advisory services using local Python scripts (risk_quantifier.py, compliance_tracker.py) and markdown references. These operations are restricted to the local environment and are aligned with the skill's stated purpose of translating technical risks into business impact.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface by consuming data from external context files. While no specific malicious patterns were found, this ingestion point could be used to influence the agent if the context file contains adversarial content.
Ingestion points: The skill is instructed to read company-context.md before responding.
Boundary markers: No explicit boundary markers or 'ignore' instructions are present to delimit the context data.
Capability inventory: The skill can execute local Python scripts and invoke other roles via [INVOKE].
Sanitization: No explicit sanitization or validation of the context file content is mentioned.

ciso-advisor