soia-meta-skill-release
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill extensively uses
subprocess.runto execute shell commands for repository management. Filesscripts/formal_release.py,scripts/release_skills.py, andscripts/install_workbuddy_experts.pyinvokegit,gh,npx, andpython3to automate pull request creation, tagging, and skill installation. These operations are triggered by user-initiated release commands and are directed at the repositories specified in the configuration. - [EXTERNAL_DOWNLOADS]: The skill triggers downloads of external packages and scripts during its execution.
scripts/release_skills.pyusesnpx skills addto install or update agent skills from remote repositories. The documentation also recommends installing the skill viaclaude plugin marketplaceornpx skills. - [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of scripts that may be retrieved from external sources.
scripts/install_workbuddy_experts.pyexecutes the official WorkBuddy registration script located at a specific path within the application bundle. It also invokes internal scripts such assoia-meta-sync-skills/scripts/sync_soia_skills.py. - [DATA_EXFILTRATION]: The skill performs network operations that involve sending local repository data to GitHub. This includes pushing code changes, creating tags, and publishing Release Notes via the
gh release createcommand. These operations are limited to the target GitHub repository configured for the release. - [PROMPT_INJECTION]: The skill ingests untrusted data from git logs to generate user-facing content (Indirect Prompt Injection). Ingestion points:
scripts/generate_release_notes.pyreads commit subjects viagit log. Boundary markers: None identified; the commit subjects are categorized and appended to theCHANGELOG.mdand GitHub Release notes. Capability inventory: The generated notes are written to the local file system (CHANGELOG.md) and sent to GitHub via theghAPI. Sanitization: Minimal; the script classifies commits based on conventional prefixes but does not filter for malicious instruction content within the commit messages.
Audit Metadata