content-strategy
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external, untrusted data including sales call transcripts, survey responses, and keyword research exports (Ahrefs/SEMrush) to generate content ideas.
- Ingestion points: Ingests data from
.agents/product-marketing.mdand user-provided transcripts or data exports mentioned in the 'Content Ideation Sources' section. - Boundary markers: The instructions do not specify any markers (like XML tags or delimiters) to isolate external data or instruct the agent to ignore embedded instructions within that data.
- Capability inventory: The skill lacks dangerous capabilities such as subprocess execution, dynamic code evaluation (
eval/exec), file writing, or network exfiltration commands. - Sanitization: No sanitization or validation logic is applied to the ingested external content.
Audit Metadata