consolidate-repos-to-agenteq
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external source repositories, including GUIDELINES.md, skill definitions, and command files.\n
- Ingestion points: Reads content from source repository directories (e.g., skills/, commands/, GUIDELINES.md) during the consolidation process.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing these files.\n
- Capability inventory: The skill has the ability to execute shell commands via npx and git, and can modify or delete files on the local system.\n
- Sanitization: No sanitization or validation of the ingested markdown or JSON content is specified before it is processed or migrated.\n- [PERSISTENCE]: The skill automates the installation of Git hooks to maintain synchronization across repositories.\n
- Evidence: Step 13 modifies various hook management files (e.g., .husky/post-checkout, lefthook.yml, .git/hooks/post-checkout) to execute npx agenteq sync automatically.\n
- Mitigation: The skill explicitly requests user confirmation before modifying or installing any hooks.\n- [EXTERNAL_DOWNLOADS]: The skill downloads and installs additional tools and logic from remote sources.\n
- Evidence: Step 5 uses npx skills add to fetch skills from the author's GitHub repository (https://github.com/sunchayn/agenteq).\n
- Context: These resources are provided by the skill's author and are integral to its stated functionality.\n- [COMMAND_EXECUTION]: The skill performs various system operations using Git and Node.js package execution.\n
- Evidence: It executes git init, git remote, git rev-parse, and npx agenteq to manage the lifecycle of the destination and source repositories.
Audit Metadata