context-budget

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes content from project files such as agents, skills, and rules to calculate token overhead. This ingestion creates a vulnerability surface where malicious instructions embedded in these audited files could attempt to influence the agent's reporting or classification behavior during the audit process.
  • Ingestion points: Specifically targets agents/*.md, skills/*/SKILL.md, rules/**/*.md, .mcp.json, and CLAUDE.md files.
  • Boundary markers: The skill instructions do not define delimiters or specific warnings to ignore instructions found within the audited content.
  • Capability inventory: The skill's primary capabilities are limited to reading local files and performing data estimation; no file-write, network exfiltration, or arbitrary command execution patterns were identified.
  • Sanitization: There is no mention of sanitizing or filtering the content of the files before the agent processes them for classification and reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 03:00 PM