The Agent Skills Directory

[NO_CODE]: The skill package is composed entirely of Markdown documentation and structured instructions for an AI agent. No executable script files (e.g., .py, .js, .sh) or binary executables are present in the provided files.
[SAFE]: Analysis of the instructions in SKILL.md and supporting references shows no evidence of malicious intent. The skill defines a set of 'Virtual Experts' to provide management advice based on established industry frameworks such as ITIL 5, COBIT, and TOGAF. No prompt injection attempts, obfuscation, or data exfiltration patterns were identified.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a minimal attack surface for indirect injection as it primarily processes user-provided scenarios for advisory purposes.
Ingestion points: User-supplied management queries and trigger phrases defined in README.md and SKILL.md.
Boundary markers: The skill implements a 'Mandatory Instructional Protocol' that requires explicit user consent before providing extended insights, serving as a logical interaction boundary.
Capability inventory: None. The skill does not invoke external tools, write to the filesystem, or perform network operations.
Sanitization: Not applicable as the skill lacks executable capabilities.

it-manager-pro