The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill's behavior aligns with its stated purpose of automating incident response documentation and communication.
[COMMAND_EXECUTION]: The skill executes the gws binary to perform Google Workspace operations. This tool is explicitly listed as a requirement in the metadata and is used for its intended purpose (Docs, Calendar, and Chat management).
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it interpolates the [Incident] placeholder into tool commands.
Ingestion points: Untrusted user input is ingested via the [Incident] placeholder in SKILL.md and used in document titles, calendar summaries, and chat messages.
Boundary markers: No delimiters or safety instructions are provided to separate the user-provided incident name from the command context.
Capability inventory: The skill utilizes the gws binary to write to Google Docs, create calendar entries, and send chat messages (SKILL.md).
Sanitization: No sanitization or validation of the user input is performed before interpolation.

recipe-post-mortem-setup