The Agent Skills Directory

[PROMPT_INJECTION]: Potential for indirect prompt injection through asset files and documentation. 1. Ingestion points: The skill reads external content from files in assets/ subdirectories and documentation using Glob and Read tools (SKILL.md). 2. Boundary markers: There are no explicit instructions or delimiters to prevent the agent from following instructions found within the audited files. 3. Capability inventory: The skill is restricted to Read, Glob, and Grep tools; it has no access to tools that allow network communication, file writing, or command execution. 4. Sanitization: No sanitization or escaping mechanisms are specified for data extracted from files before it is placed into the markdown report.

asset-audit