The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase to generate documentation, creating a surface for indirect prompt injection.
Ingestion points: The skill uses Read, Glob, and Grep tools to scan project root files, configuration files (e.g., wrangler.jsonc, package.json), entry points, directory structures, and database schema/migration files as described in the 'Workflow' section of SKILL.md.
Boundary markers: The instructions do not include explicit delimiters or warnings to the agent to ignore instructions embedded within the source files it reads.
Capability inventory: The skill has Write, Edit, and Bash tools allowed in its frontmatter, which could be misused if the agent obeys malicious instructions found in the analyzed source code.
Sanitization: There is no mention of sanitizing or validating the content read from files before it is processed or used to generate documentation output.

project-docs