The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
Ingestion points: Untrusted data enters the agent's context through external research via WebFetch and by reading user-provided specification files from docs/specs/.
Boundary markers: The workflow does not utilize delimiters or specific instructions to ignore embedded commands within the ingested data.
Capability inventory: The agent has the ability to write to files (rewriting specifications), perform network operations (WebFetch), and spawn subagents (Task).
Sanitization: There is no evidence of content validation or escaping before the data is processed or used to update local documents.
[EXTERNAL_DOWNLOADS]: The skill uses WebSearch and WebFetch to gather information from the internet to resolve research tasks.
[COMMAND_EXECUTION]: The skill employs Grep, Glob, and Read tools to search and retrieve content from the local codebase.

resolve-beagle