The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute scripts defined in the target project's configuration, such as npm run lint and npm run test:coverage in Phase 4, as well as npm audit and npm outdated in Phase 5.
[DATA_EXPOSURE]: During Phase 1 (Discovery), the skill explicitly instructs the agent to scan for and read sensitive environment files, including .env* and .env.example, which commonly contain secrets and configuration credentials.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external codebases, creating a surface for indirect prompt injection.
Ingestion points: The skill uses Read, Glob, and Grep tools to ingest the entire content of a project directory (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the analyzed code.
Capability inventory: The skill has access to powerful tools including Bash, Read, Glob, and Grep.
Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed by the agent.

codebase-analysis