project-version-upgrade

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes external data and local project files to generate and execute an upgrade plan.
  • Ingestion points: The skill reads project manifest files (package.json, *.csproj, global.json) in SKILL.md and fetches external migration documentation using the context7 tool.
  • Boundary markers: There are no instructions defining the use of delimiters or specific warnings to ignore embedded instructions within the ingested data.
  • Capability inventory: The skill utilizes an 'implementer' to edit local files and executes shell commands for build and test verification across its execution stages.
  • Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from manifests or external guides.
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using development toolchains to verify project state and apply updates.
  • Evidence: Mentions the use of 'dotnet build', 'dotnet test', and 'ng update' commands in SKILL.md and references/upgrade-playbooks.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:05 PM
Security Audit — agent-trust-hub — project-version-upgrade