skills/ahgraber/skills/spec-kit-tasks/Gen Agent Trust Hub

spec-kit-tasks

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script scripts/check-prerequisites.sh to resolve feature paths and validate prerequisites. This is an expected operational step for the tool's intended functionality.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and templates from the official Spec Kit repository on GitHub, which is a well-known and recognized service for development resources.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and processing external project files to generate output. This is a common pattern for design-to-task automation tools and is handled at a safe severity level given the skill's purpose.
  • Ingestion points: Reads from plan.md, spec.md, research.md, data-model.md, contracts/, and quickstart.md within the feature specification directory.
  • Boundary markers: Absent; the workflow does not define specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded in the input documents.
  • Capability inventory: The agent has the ability to execute local shell scripts (scripts/check-prerequisites.sh) and write files (tasks.md) to the local file system.
  • Sanitization: No explicit content validation or sanitization of the input documents is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 12:44 PM