The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its requirement to process untrusted external data with high-privilege tools.
Ingestion points: The agent is instructed to analyze a codebase (Target: $ARGUMENTS) using Read, Glob, and Grep tools to determine context and compliance evidence (SKILL.md).
Boundary markers: The instructions lack delimiters or safety warnings directing the agent to ignore natural language instructions that might be embedded within the scanned files.
Capability inventory: The skill is granted access to the Bash, Write, and Task tools, which allow for shell command execution and file system modifications, creating a high-impact vector if the agent is manipulated (SKILL.md).
Sanitization: There is no implementation of validation or sanitization for the content read from the external codebase before it is processed by the agent.

masvs-checklist