The Agent Skills Directory

[SAFE]: Analysis of the skill instructions and reference materials found no evidence of prompt injection, data exfiltration, or obfuscation. The content focuses on marketing strategy, TCPA/GDPR compliance, and platform comparisons.
[NO_CODE]: The skill is composed strictly of Markdown documentation and JSON evaluation files. It does not include Python, Node.js, or shell scripts, eliminating the risk of direct malicious code execution within the skill itself.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by ingesting external context from project files and user inputs. 1. Ingestion points: Product marketing context is read from .agents/product-marketing.md or .claude/product-marketing.md (SKILL.md). 2. Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore embedded commands within ingested context. 3. Capability inventory: The skill's primary capabilities are generating SMS copy templates and marketing recommendations (SKILL.md, references/sequence-templates.md). No subprocess calls, file writes, or network operations are present in any skill files. 4. Sanitization: Absent. There are no explicit sanitization or filtering steps defined for external content.

sms