afk-coding-tradeoffs
Warn
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to prompt the user to install an external dependency from a personal, non-authoritative GitHub repository if a specific tool is missing.
- Evidence: In
SKILL.md, the agent is directed to ask the user to runnpx skills add https://github.com/leoreisdias/truss-frameworkiftruss-evaluationis not found. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from various external project materials to inform its reasoning and output.
- Ingestion points: The workflow in
SKILL.md(Step 2: Load prior context) specifies reading roadmaps, planning documents, requirement notes, specs, and tickets. - Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are defined for the ingested data.
- Capability inventory: The skill has the capability to generate mandatory decision artifacts (files) based on the processed information.
- Sanitization: There are no instructions for sanitizing or validating the contents of the external documents before they are incorporated into the agent's context.
Audit Metadata