content-strategy

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data, which creates a surface for indirect prompt injection attacks where malicious instructions could be embedded in the analyzed content.
  • Ingestion points: The skill explicitly instructs the agent to analyze 'Keyword Data', 'Call Transcripts', 'Survey Responses', and 'Forum Research' results provided by the user or fetched via web search (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these data sources.
  • Capability inventory: The skill utilizes read access to project context files (e.g., .agents/product-marketing.md) and web search tools. No high-risk capabilities such as arbitrary command execution (exec/eval), file system writes, or direct network exfiltration were detected.
  • Sanitization: Absent. There are no instructions provided to sanitize, validate, or filter the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:13 AM
Security Audit — agent-trust-hub — content-strategy