skills/maxgfr/skills/blueprint/Gen Agent Trust Hub

blueprint

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions explicitly direct the agent to execute shell commands defined in the "Verify" field of the generated plan file.
  • Evidence: SKILL.md specifies "Run each Verify once (2>&1 | tail -5)". The references/artifact.md file defines the schema for these commands, where <command> is provided as a template for execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection as it ingests data from the repository to formulate execution steps.
  • Ingestion points: The skill reads from the existing repository (SKILL.md step 1) and accepts user input to define "Locked constraints" (referenced in references/grill.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore commands embedded within the repository files it reads.
  • Capability inventory: The agent has the capability to execute shell commands (SKILL.md) and invoke other skills (such as the build skill).
  • Sanitization: There is no evidence of sanitization or validation of the commands generated from the repository facts before they are executed in the verification step.
  • [DYNAMIC_EXECUTION]: The skill performs dynamic execution by generating a plan containing shell commands and then immediately executing those commands.
  • Evidence: The workflow involves writing a plan to docs/plans/<YYYY-MM-DD>-<slug>.md and then running each Verify command once as specified in the second part of the SKILL.md instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 05:38 PM