skills/jotafurtado/on-track/ot-spec/Gen Agent Trust Hub

ot-spec

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local and sibling shell scripts to perform repository indexing and structural validation. This includes running scripts located in a sibling skill directory and a local script within the skill's own directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of intent.md from the target repository to generate specification files, task lists, and decision logs. Malicious instructions embedded in the user-provided intent file could potentially influence the agent's behavior during the specification drafting phase.
  • Ingestion points: Reads on-track/tracks/NNN-slug/intent.md to classify questions and derive project constraints.
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore potential instructions embedded within the intent file.
  • Capability inventory: The skill has the capability to write multiple files (spec.md, tasks.md, decisions/*.md) and execute shell scripts (on-track-index.sh, on-track-gate.sh).
  • Sanitization: No sanitization or filtering of the intent file content is described before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 04:21 AM