The Agent Skills Directory

[SAFE]: No malicious code, obfuscation, or dangerous command executions were detected in the skill instructions or evaluation files.
[PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to read external project context files.
Ingestion points: Reads .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md to establish project context (specified in SKILL.md).
Boundary markers: None; the skill does not specify the use of delimiters or instructions to ignore commands within the ingested files.
Capability inventory: The skill does not define any tools, network operations, file writing, or subprocess execution capabilities.
Sanitization: No validation or sanitization of the content of the ingested files is specified.
Analysis: While the ingestion of untrusted data is a known surface, the total absence of executable tools or network access within this skill renders the risk negligible.

community-marketing