The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various diagnostic and administrative commands using npx @insforge/cli. These include system health checks (diagnose), log retrieval (logs), database management (db query, db policies), and secret retrieval (secrets get).
[EXTERNAL_DOWNLOADS]: Uses npx to download and execute the @insforge/cli package from the npm registry. This package belongs to the 'insforge' organization, which matches the skill's author and intended vendor context.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the combination of high-privilege capabilities and the ingestion of untrusted data.
Ingestion points: The skill reads content from multiple log sources (insforge.logs, postgREST.logs, postgres.logs, function.logs) and processes user-provided natural language descriptions in the diagnose --ai command.
Boundary markers: No explicit delimiters or instructions are used to separate ingested data from agent instructions.
Capability inventory: The agent has access to sensitive tools including npx @insforge/cli db query (arbitrary SQL execution), npx @insforge/cli secrets get (access to project secrets), and npx @insforge/cli functions code (source code retrieval).
Sanitization: There are no mentioned mechanisms for sanitizing or escaping the data retrieved from logs before it is processed by the agent.

insforge-debug