content-calendar-sms

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access to sensitive system data were detected. The skill's behavior is consistent with its stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it reads and processes data from an external context file that could be influenced by an attacker.
  • Ingestion points: The file .agents/social-media-context-sms.md is read in full during the initialization phase (Step 1).
  • Boundary markers: There are no specific delimiters or markers used to isolate the data read from the context file from the system's instructions.
  • Capability inventory: The skill has the ability to create social media posts and fetch analytics data via tool calls to the BlackTwist MCP (Step 5 and Step 7).
  • Sanitization: No validation or filtering is performed on the content of the context file before it is used to populate variables for the planning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 11:20 AM