agent-context

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a documentation utility, analyzing project structure and configuration files to create guidance for agents. Its behavior is entirely consistent with its stated purpose.
  • [PROMPT_INJECTION]: Analysis of the skill's indirect prompt injection surface:
  • Ingestion points: SKILL.md (Step 2) reads AGENTS.md, README.md, workspace/package manifests, task/build config, CI workflows, and .specflow/ docs.
  • Boundary markers: The instructions do not specify any delimiters or explicit warnings to the agent to ignore instructions embedded within the ingested data.
  • Capability inventory: The skill is designed to synthesize markdown content and write AGENTS.md files. It does not possess network capabilities or shell execution tools.
  • Sanitization: No explicit sanitization or filtering of input data is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 04:13 PM
Security Audit — agent-trust-hub — agent-context