wiki-merge

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script using uv run python scripts/wiki-merge.py. This operation relies on the security and integrity of the local scripts/wiki-merge.py file, which is not included in the skill definition.\n- [INDIRECT_PROMPT_INJECTION]: The skill architecture interpolates user-provided slugs into a shell command template, which could be exploited for argument injection if input is not properly validated.\n
  • Ingestion points: CLI arguments <winner-slug> and <loser-slugs> defined in SKILL.md.\n
  • Boundary markers: No explicit delimiters or instructions are provided to isolate user-supplied slugs from the shell command instructions.\n
  • Capability inventory: The skill utilizes Bash and Read tools, granting it the ability to read, write, and delete files within the ~/vault/ directory.\n
  • Sanitization: The instructions do not define any sanitization, escaping, or validation logic for the external slug content before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 06:17 AM
Security Audit — agent-trust-hub — wiki-merge