The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for sales enablement tasks such as pitch decks, one-pagers, and objection handling. No malicious instructions or safety bypasses were identified in the primary SKILL.md or reference files.
[SAFE]: No obfuscated content, Base64 strings, or hidden instructions were detected in the skill files or metadata fields.
[SAFE]: The skill does not perform any network operations or download external scripts. References to external tools (like 'Introw') are documented through local integration guides and do not involve silent remote code execution.
[SAFE]: No dangerous command execution, privilege escalation, or persistence mechanisms are present in the skill body, reference scripts, or environment configuration.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection via the ingestion of local context files and user-provided inputs. However, no exploitable capabilities were found to exist in the skill's environment.
Ingestion points: Ingests context from user prompts and local files such as .agents/product-marketing.md.
Boundary markers: Explicit delimiters or instructions to ignore embedded commands in external data are not present.
Capability inventory: The skill is restricted to text generation; no network access, file-writing, or shell execution capabilities are available in the provided scripts.
Sanitization: No explicit sanitization or filtering of external content is implemented.

sales-enablement