The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface. Malicious instructions could be embedded in the product documentation files that the agent is instructed to read.
Ingestion points: Reads files from the .chalk/docs/product/ directory (SKILL.md).
Boundary markers: The workflow does not specify the use of delimiters or 'ignore embedded instructions' markers when processing the content of these files.
Capability inventory: The skill has access to Read, Glob, Grep, and Write tools, allowing it to read and create files in the local environment.
Sanitization: There is no mention of sanitization, validation, or filtering of the content read from the external local files before it is processed by the agent.

analyze-competitors