The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and reference documentation. No malicious patterns, obfuscation, or unauthorized data access mechanisms were identified.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion point for external data by instructing the agent to read product marketing context files (e.g., .agents/product-marketing.md). While this creates a potential surface for indirect prompt injection, the risk is assessed as safe because the skill lacks exploitable capabilities such as file modification, network operations, or command execution.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, product-marketing-context.md (via Initial Assessment section in SKILL.md).
Boundary markers: Absent; instructions do not explicitly tell the agent to ignore embedded instructions in these files.
Capability inventory: None; the skill's purpose is limited to providing textual strategic advice and does not involve subprocess calls, file writes, or network access.
Sanitization: Absent; the agent is directed to read the raw content of the context files.

free-tools