The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as customer needs and prospect communications. It mitigates potential injection risks by explicitly instructing the agent to treat quoted text as evidence rather than instructions. Furthermore, it requires verification that no third-party input expands the agent's execution authority.
[SAFE]: No scripts, dependencies, or remote code execution patterns were found. The skill is purely instructional and documentation-focused, with no data exfiltration or credential safety issues identified.

sales-proposal