The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources which could contain instructions to manipulate agent behavior.
Ingestion points: Data enters the context via gpd reviews list (which includes review text) and gpd vitals errors reports search (which includes crash report details).
Boundary markers: The skill does not define specific delimiters or instructions to treat fetched external content as data rather than instructions.
Capability inventory: The skill possesses significant capabilities, including network write operations via gpd reviews reply, deployment capabilities via gpd publish, and destructive monetization actions via gpd monetization subscriptions delete.
Sanitization: There is no evidence of filtering or sanitization of review text or crash reports before they are processed by the agent.

gpd-cli