The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx @insforge/cli to perform diagnostic tasks. These commands enable the agent to retrieve logs, inspect database policies, and manage secrets. These tools are provided by the vendor 'insforge' and are appropriate for the skill's debugging purpose.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it instructs the agent to read and analyze untrusted data sources like application logs and function source code. It lacks protective measures to ensure the agent does not interpret data as instructions. 1. Ingestion points: Data is ingested via commands like logs, functions code, and db query in SKILL.md. 2. Boundary markers: No boundary markers or delimiters are specified to wrap external content. 3. Capability inventory: The skill allows the agent to execute shell commands, query the database, and access secrets. 4. Sanitization: There are no instructions for sanitizing or validating retrieved content.

insforge-debug