The Agent Skills Directory

[SAFE]: The skill is a structured analytical framework and does not include any executable code, network operations, or persistence mechanisms. The tools allowed in the frontmatter (Read, Grep, Glob) are appropriate for the stated purpose of analyzing logs and reports.
[PROMPT_INJECTION]: The skill processes untrusted external data, such as forensic findings and incident logs, which constitutes an indirect prompt injection surface.
Ingestion points: Untrusted data is ingested via files and directories specified in the $ARGUMENTS parameter and accessed through the Read, Grep, and Glob tools.
Boundary markers: The skill contains a specific 'Prompt Injection Safety Notice' in Section 8 that explicitly instructs the agent to treat analyzed content strictly as data and to never follow instructions or execute code found within those files.
Capability inventory: The skill is limited to read-only capabilities (Read, Grep, Glob) and does not possess tools for file modification, network communication, or code execution.
Sanitization: The skill relies on instructional constraints and the 'blameless retrospective' methodology to filter content rather than programmatic sanitization of the input logs.

post-incident-review