The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and display alert metadata, such as titles and summaries, which are sourced from external integrations and may contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Alert data is fetched via gcx irm oncall alert-groups list and gcx irm oncall alert-groups get <id> as described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to treat the alert content as untrusted data.
Capability inventory: The agent can modify alert states (acknowledge, silence, resolve) using the gcx tool via Bash.
Sanitization: No sanitization or filtering of alert content is specified before it is presented to the agent.
[COMMAND_EXECUTION]: The skill relies on the Bash tool to execute gcx CLI commands for retrieving and managing Grafana OnCall data. While these are standard operational commands for the Grafana ecosystem, they involve executing shell commands that interface with a remote service.

oncall-triage