The Agent Skills Directory

[SAFE]: The skill performs legitimate operations such as reading git logs and GitHub PR information to generate documentation. These activities are consistent with its primary purpose as an incident review tool.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to the ingestion of untrusted incident descriptions and logs.
Ingestion points: Data enters the agent context through the $ARGUMENTS variable in SKILL.md.
Boundary markers: Input data is encapsulated within <incident_context> tags.
Capability inventory: The skill has the ability to execute git and GitHub CLI commands and write files to the local directory.
Sanitization: The skill does not explicitly sanitize or validate the content of the incident description before using it to guide analysis.

debrief