platform-strategy-sms
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is informational, providing tactical advice for social media platforms. It does not include executable scripts, network requests, or access to sensitive system resources.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file (
.agents/social-media-context-sms.md) to personalize its advice, creating a potential surface for indirect prompt injection. However, this surface is not exploitable as the skill lacks any capabilities to perform network exfiltration, filesystem writes, or command execution. - Ingestion points: The skill reads from
.agents/social-media-context-sms.mdin Step 1 to gather user goals and audience details. - Boundary markers: None; the skill does not use specific delimiters or instructions to ignore embedded commands within the context file.
- Capability inventory: None; the skill does not request or use any tools for system modification or external communication.
- Sanitization: None; ingested content is used directly to inform the agent's strategic response.
Audit Metadata