developer-audience-context

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from the local project environment, including GitHub Issues, documentation, and blog posts, to generate audience personas. This presents a surface for indirect prompt injection where adversarial instructions hidden in these files could manipulate the agent's output or logic during the analysis.
  • Ingestion points: Processes README.md, /docs, index.html, package.json, GitHub Issues, and existing blog posts.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the skill's instructions and the untrusted project data it is processing.
  • Capability inventory: The skill utilizes file system read and write permissions to analyze the codebase and store the context in the .agents/ directory.
  • Sanitization: The skill does not perform any validation or sanitization of the content ingested from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 01:32 PM
Security Audit — agent-trust-hub — developer-audience-context