skills/iamursky/sokrati/escurca/Gen Agent Trust Hub

escurca

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied professional texts (such as emails, landing pages, and reports) to provide edits and critiques, creating a surface where malicious instructions embedded in the processed text could potentially influence agent behavior.
  • Ingestion points: User-provided text content passed to the agent for editing and review, as described in the skill's activation triggers (SKILL.md, README.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the text strictly as data or to ignore embedded commands.
  • Capability inventory: The skill is granted permissions to read, write, and edit files, and to grep/glob the filesystem, which could be leveraged if an injection were successful (SKILL.md).
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 07:17 AM
Security Audit — agent-trust-hub — escurca