The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses natural instructional language to define a role. It contains no attempts to bypass safety filters, extract system prompts, or override agent behavioral constraints. The 'Critical Rules' are standard professional guidelines for change management practice.
[DATA_EXFILTRATION]: There are no commands or functions that access sensitive local files (such as SSH keys or environment variables) or attempt to transmit data to external servers. The skill is entirely descriptive and template-based.
[REMOTE_CODE_EXECUTION]: No remote script downloads (e.g., curl|bash) or package installations (pip/npm) were detected. The skill does not include any executable scripts or binary files.
[COMMAND_EXECUTION]: The skill contains no shell commands, subprocess calls, or dynamic execution patterns. It provides text-based frameworks and assessment guides for human interpretation or LLM advice generation.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were found. The instructions focus on organizational consulting rather than technical configurations.
[OBFUSCATION]: The content is written in plain, legible Markdown. No Base64-encoded strings, zero-width characters, or homoglyph substitutions were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process organizational data (stakeholder maps, readiness scores), it lacks any computational capabilities or tool access that could be exploited via malicious input. The risk is negligible as it functions as a purely instructional framework.

agency-change-management-consultant