b2c-marketing

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a companion capability using npx skills add post-bridge-hq/agent-mode. This involves downloading and integrating external code from the developer's repository into the agent environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external performance data and logs to provide growth coaching, which creates a potential surface for instructions embedded in that data to influence agent behavior.
  • Ingestion points: Social media performance metrics provided by the user and the tracking log located at workspace/memory/b2c-marketing-log.md.
  • Boundary markers: None explicitly defined in the coaching instructions to distinguish between data and commands.
  • Capability inventory: The skill references the use of the post-bridge companion skill for API interaction and media upload via postbridge-cli.
  • Sanitization: No specific validation or filtering logic is described for the ingested performance data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:22 PM
Security Audit — agent-trust-hub — b2c-marketing