design-content-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to analyze external content from the Top 10 SERP results to evaluate Information Gain and audit existing inventory for content decay. This creates a surface for indirect prompt injection where malicious instructions embedded in third-party web content or existing site files could influence the agent's behavior.
- Ingestion points: The agent ingests untrusted data from Top 10 SERP competitors (described in
SKILL.mdandreferences/information-gain-and-decay-triage.md) and existing site content. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the external data being processed.
- Capability inventory: The skill is configured with
write_file,edit_file, andcreate_filepermissions, which could be misused if the agent obeys instructions hidden in the ingested data. - Sanitization: No explicit sanitization, filtering, or validation mechanisms are described for the external content before it is processed or used to generate outputs.
Audit Metadata