opencode-conversation-recall

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the opencode db command-line utility to perform database operations, including retrieving paths and running SQL queries.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it retrieves and processes historical conversation content.
  • Ingestion points: Conversation text is ingested from the part table via SQL queries in SKILL.md.
  • Boundary markers: No delimiters or instructions are specified to prevent the agent from following commands embedded in the retrieved historical text.
  • Capability inventory: The agent has the ability to execute database commands via opencode db.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved chat history before it is processed by the agent.
  • [DATA_EXFILTRATION]: The skill accesses sensitive information, including full conversation histories, project IDs, and local directory paths stored in the SQLite database.
  • [COMMAND_EXECUTION]: The workflow for searching and reading specific sessions uses string interpolation for SEARCH_TERM and SESSION_ID, creating a surface for SQL injection against the local database if inputs are not properly escaped by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 11:57 PM