The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted strategic documents provided by the user, creating a vulnerability surface for indirect prompt injection. * Ingestion points: In SKILL.md (Step 1), the agent is instructed to use read_file to load external documents such as business plans, market research, and validation reports. * Boundary markers: The instructions do not specify the use of delimiters or provide the agent with explicit directives to ignore any embedded instructions or 'jailbreak' attempts found within the analyzed documents. * Capability inventory: The agent has access to file system tools, specifically read_file for reading user data and write_file for generating the final critique report in the project root. * Sanitization: There is no evidence of content sanitization, escaping, or validation of the text extracted from the external documents before it is processed or included in the output report.

plan-critiquer