skills/codagent-ai/agent-skills/spec/Gen Agent Trust Hub

spec

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its core functionality of reading and processing untrusted data from proposal files and neighboring specifications to generate new content.\n
  • Ingestion points: The skill reads project proposals and existing spec files from the workspace to identify capabilities and ensure consistency.\n
  • Boundary markers: The skill defines a mandatory 'HARD-GATE' procedure, explicitly instructing the agent not to write any files until it has presented the proposed requirements and scenarios to the user and received approval.\n
  • Capability inventory: The skill possesses the capability to write and modify files on the local filesystem, specifically creating specification documents in the specs/ directory.\n
  • Sanitization: No explicit instructions for sanitizing, escaping, or validating the input data from ingested files are provided in the instructions.\n- [NO_CODE]: The skill is composed entirely of natural language instructions in a markdown file and does not include any executable scripts or binary components.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:48 AM