opencode-reconstituter

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using pnpm to interact with a local CLI tool located in packages/reconstituter. This is used to index, search, and run project reconstruction tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes 'OpenCode sessions', which may contain untrusted data that could influence the agent's behavior or output.
  • Ingestion points: OpenCode session data accessed during the index and search steps in SKILL.md.
  • Boundary markers: None provided; the skill does not specify delimiters or instructions to disregard potential commands embedded within the session data.
  • Capability inventory: The skill has the ability to execute local shell commands via pnpm and perform file system writes to the .reconstitute/output directory.
  • Sanitization: There is no mention of sanitization, filtering, or validation of the session data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:49 AM
Security Audit — agent-trust-hub — opencode-reconstituter