The Agent Skills Directory

[SAFE]: The skill contains no signs of data exfiltration, hardcoded credentials, or unauthorized network operations. Its stated purpose aligns with its requested tool permissions.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it is designed to ingest and process project-related files (such as design documents and source code) and act upon them using high-privilege tools like Bash and Task.
Ingestion points: The skill reads content from design/gdd/ and project source files using Read, Glob, and Grep.
Boundary markers: The instructions do not define clear delimiters or warnings to treat ingested file content as untrusted data.
Capability inventory: The agent has access to Bash for shell execution, Write/Edit for file system modification, and Task for spawning autonomous subagents.
Sanitization: There are no instructions for sanitizing or validating the content of the design documents before they are passed to subagents or used to generate code.

team-combat