The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is explicitly designed to ingest and synthesize untrusted external data, including customer interview notes, document reviews, and RFP requirements. The instructions lack guidance on implementing boundary markers or sanitization when processing this external content, which could allow maliciously crafted input in a document to influence the agent's behavior.
Ingestion points: references/discovery_and_requirements.md (interviews, document review, workshops), references/rfp_poc_and_handoff.md (parsing RFPs), references/solutions_architect_scope.md (questionnaires).
Boundary markers: No delimiters or "ignore embedded instructions" warnings are defined in the reference materials.
Capability inventory: The skill is purely instructional and does not include tools or scripts for network operations, subprocess execution, or direct file system manipulation.
Sanitization: No methods for escaping or validating external content are mentioned.
[NO_CODE]: The skill consists entirely of markdown documentation and architectural templates. It does not include any executable scripts, automated tools, or remote code downloads.

solutions-architect