The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Jira issues via the Atlassian MCP. Ingestion points: Data is pulled using the mcp__atlassian__searchJiraIssuesUsingJql tool and saved to snapshot.json. Boundary markers: The skill instructions do not provide explicit delimiters or directives for the agent to ignore instructions embedded within the issue data. Capability inventory: The skill has the ability to execute local scripts and call MCP tools to perform Jira operations. Sanitization: Data is normalized into a structured JSON schema by scripts/jira_snapshot_bridge.py before being analyzed by the agent, which mitigates simple injection attempts.
[COMMAND_EXECUTION]: The skill executes local Python scripts provided within the package (scripts/pm_goal_router.py, scripts/jira_snapshot_bridge.py, scripts/delivery_loop_gate.py) to perform goal routing, data bridging, and governance gating. These operations are transparent and scoped to the project's delivery lifecycle.

pm-skills