The Agent Skills Directory

[SAFE]: The skill implements a structured workflow for process documentation within a defined business framework.
[PROMPT_INJECTION]: No patterns indicative of prompt injection, behavior overrides, or safety filter bypasses were detected in the instructions.
[DATA_EXFILTRATION]: The skill accesses local project directories for SOP storage and template reading. It contains no network operations or indicators of data exfiltration.
[REMOTE_CODE_EXECUTION]: No commands for external downloads, package installations, or remote script execution were found.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests content from external markdown files (capture and triage data), it does so to populate templates for human-readable documentation. The risk is minimized by the lack of automated tool execution based on the ingested content during the authoring phase.

sop-authoring