The Agent Skills Directory

[SAFE]: No security issues were detected. The skill contains procedural instructions and documentation for using the Filigree issue tracking system, including CLI command usage, swarm coordination, and triage patterns.
[DATA_EXFILTRATION]: The skill documentation refers to standard API endpoints for the Filigree service (e.g., /api/files/_schema, /api/entity-associations). These represent normal tool communication and do not constitute exfiltration.
[PROMPT_INJECTION]: The skill processes untrusted data which presents a surface for indirect prompt injection. * Ingestion points: The agent reads external content via filigree show, filigree get-comments, and issue_search (described in references/commands.md). * Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the guidelines. * Capability inventory: The agent can execute filigree CLI commands and MCP tools to modify the database and interact with file records. * Sanitization: No explicit sanitization or validation of input data is mentioned in the skill files. * Note: This surface is inherent to the tool's primary purpose as an issue tracker.

filigree-workflow