The Agent Skills Directory

[PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill's primary function involves reading and analyzing untrusted repository files, which could contain instructions designed to manipulate the agent's behavior.
Ingestion points: Analyzes project files including CLAUDE.md, package.json, and source code via Read, Grep, and Glob tools.
Boundary markers: Absent. The instructions do not define clear delimiters or provide the agent with directives to ignore instructions embedded within the processed content.
Capability inventory: Uses Bash, Read, Grep, and Glob tools for repository structure analysis and maturity auditing.
Sanitization: Absent. There is no evidence of validation or sanitization of the content extracted from the files before it is processed by the agent.

harness-diagnostics