The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its ingestion of untrusted external content.\n- Ingestion points: The agent reads and processes data from docs/reverse/{analysis}/manifest.json, docs/reverse/{analysis}/02-logic-{component}.md, and various source files.\n- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present when external file content is interpolated into the agent's context.\n- Capability inventory: The skill allows the use of powerful tools including Bash, Write, Read, and Grep, which increases the potential impact of a successful injection.\n- Sanitization: There is no evidence of validation, filtering, or sanitization of the content from the external files before it is processed.

re-verify-logic