The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from various project artifacts which could contain malicious instructions.
Ingestion points: The workflow involves reading PRD files, epic files, user stories, and architecture documents (referenced in docs/prd/ and docs/architecture/ per resources/core-config.yaml).
Boundary markers: The instructions do not specify the use of clear delimiters or explicit directives for the agent to ignore instructions embedded within the processed project files.
Capability inventory: The skill's primary capability is generating 'Sprint Change Proposal' documents in the docs/change-proposals/ directory. It does not have access to tools for arbitrary shell command execution or network operations.
Sanitization: There is no explicit sanitization or validation logic applied to the content read from external project files.
[EXTERNAL_DOWNLOADS]: The documentation references the author's official GitHub repository (github.com/Gamaroff/agent-skills) for shared specifications and resource links. These are legitimate references to the vendor's own infrastructure.

correct-course