Skills
skills/guillempuche/ai-standards/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts and Git commands as part of the intended release workflow. * It runs scripts ./scripts/generate-individual-repos.sh and ./scripts/deploy-individual-repos.sh to prepare and push code. * It performs git add, git commit, and git push to manage repository versioning.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing data from skill and agent files. * Ingestion points: Reads content from the skills/ and agents/ directories. * Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are used. * Capability inventory: Shell script execution and Git push operations. * Sanitization: No sanitization or validation of the file contents before processing is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 04:57 AM