marketing-social-media-strategist

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ability to ingest untrusted data and perform file system operations.
  • Ingestion points: The tools definition in SKILL.md includes WebFetch and WebSearch for retrieving data from external web sources.
  • Boundary markers: The instructions lack any boundary markers or explicit safety directives to the agent to ignore instructions embedded within the data it fetches.
  • Capability inventory: The agent is granted Write and Edit tools as defined in the tools metadata, which could be misused if the agent is manipulated by malicious web content.
  • Sanitization: There is no evidence of input validation or sanitization for data retrieved through the web-based tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — marketing-social-media-strategist