The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute PagerDuty CLI commands (pd auth, pd incident list, etc.) and Node.js helper scripts for data processing and analysis.
[EXTERNAL_DOWNLOADS]: Mentions the PagerDuty CLI (martindstone/pagerduty-cli), a well-known community utility for interacting with the PagerDuty REST API.
[PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically PagerDuty incident logs and notes, which could contain adversarial content intended to influence the agent.
Ingestion points: Incident details, log entries, and notes are fetched via pd incident log and pd incident notes as described in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the prompt templates when processing this data.
Capability inventory: The skill possesses significant capabilities including Bash execution, node script execution, and Write/Edit tools for report generation.
Sanitization: The helper scripts scripts/parse-log.js and scripts/parse-notes.js perform structural filtering by extracting specific JSON fields, but they do not sanitize or escape the string content within those fields.

pagerduty-oncall