The Agent Skills Directory

[SAFE]: The skill consists of markdown templates and instructional guidance for sales enablement tasks. It does not perform any autonomous actions, file system modifications, or network requests.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context from files like .agents/product-marketing.md and references/deck-frameworks.md. This represents a potential ingestion point for untrusted data if these files are externally controlled; however, the skill mitigates this by enforcing a 'draft-only' policy and requiring explicit human approval for the 'final audience, claims, and version' before any asset is delivered.- [CREDENTIALS_SAFE]: No hardcoded API keys, tokens, or sensitive credentials were found. The skill explicitly states that any necessary credentials must come from the host session and warns against pasting them into skill files.- [EXTERNAL_DOWNLOADS]: The skill does not initiate any external downloads or install third-party packages at runtime. References to external platforms like Introw are advisory and require manual verification of security and data-export behavior by the user.- [DYNAMIC_CONTEXT_INJECTION]: No use of the exclamation-backtick syntax for shell command execution at load time was found.

suede-sales-enablement