itsol-repo-memory

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon repository-level policies, workflow restrictions, and verification commands defined in a .itsol.md file.
  • Ingestion points: The agent is instructed to read .itsol.md at the start of work and before choosing implementation or verification strategies as documented in SKILL.md and references/01-usage-priority-and-updates.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential injections within the policy file; it treats the file as a canonical contract.
  • Capability inventory: Based on the policy file's content, the agent can be steered to execute specific shell commands, such as qa.commands and verification commands, and adjust its operational mode through allowed_modes and execution presets.
  • Sanitization: There is no evidence of command sanitization or validation for instructions read from the .itsol.md file beyond initial user confirmation during the initialization process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:31 PM
Security Audit — agent-trust-hub — itsol-repo-memory