codebase-intel

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute commands through a vendor-specific CLI utility, wednesday-skills. These operations include querying codebase metadata, performing impact analysis, and maintaining dependency graphs. It also leverages standard tools like git (for history and diffs) and sqlite3 (to query local database files).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and processing data from the local repository.
  • Ingestion points: The agent ingests data from git log output, git diff content, .wednesday/codebase/MASTER.md, and the results of SQL queries against .wednesday/graph.db.
  • Boundary markers: The instructions do not define clear delimiters or provide warnings to the agent to treat data from these files as untrusted content.
  • Capability inventory: The skill has permissions to execute multiple shell commands via wednesday-skills, git, and sqlite3, and has read access to project files.
  • Sanitization: There is no mention of sanitizing, escaping, or validating the data retrieved from the codebase before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:41 PM
Security Audit — agent-trust-hub — codebase-intel