The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local commands for project management and diagnostics.
Runs chase commands for installation (chase install .), error reporting (chase errors), and log retrieval (chase logs).
Executes a local shell script .agents/skills/linear-curl-issue-ops/scripts/linear_graphql.sh to interact with the Linear API.
[DATA_EXFILTRATION]: The skill facilitates communication with the Linear project management service (linear.app).
Instructs the agent to post implementation summaries, test results, and status updates to Linear tickets. This is a standard and transparent development workflow.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external Linear tickets which could potentially contain malicious instructions.
Ingestion points: Reads ticket titles, descriptions, and acceptance criteria from linear.app URLs.
Boundary markers: None explicitly defined to separate external ticket content from system instructions.
Capability inventory: File system writes (updating STATUS.md, SPEC.md, etc.) and shell command execution (chase, local scripts).
Sanitization: No explicit sanitization or validation of retrieved ticket content is mentioned.

development