The Agent Skills Directory

[SAFE]: The skill's instructions and metadata are consistent with its stated purpose of repository analysis. No malicious behaviors such as prompt injection, data exfiltration, or obfuscation were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code repositories, which presents a surface for indirect prompt injection. However, the risk is assessed as safe because the listed tools are restricted to read-only operations and there are no instructions for exfiltration or dynamic execution.
Ingestion points: Analyzes arbitrary repository files including READMEs, configuration files, and source code.
Boundary markers: Absent; the instructions do not provide delimiters or specific warnings for the agent to ignore instructions embedded within the analyzed code.
Capability inventory: Read-only operations utilizing glob, grep, and read tools.
Sanitization: None specified for the content read from the repository.

repo-analysis