content-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional content for planning blog posts, topic clusters, and marketing strategies. It does not contain any executable code, obfuscation, or remote resource fetches.
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by instructing the agent to ingest and analyze external data from customer research, sales transcripts, and web searches.
- Ingestion points: Reads
.claude/product-marketing-context.md, keyword exports, sales/support transcripts, survey data, and web results from forums or competitors (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested text.
- Capability inventory: The skill relies on standard agent capabilities for file reading and web searching to gather context.
- Sanitization: No explicit content sanitization or validation steps are included for the data sources. This surface is standard for research-oriented tools and is consistent with the skill's primary purpose.
Audit Metadata