overreliance
Detects systems that treat LLM output as authoritative fact in consequential decisions without human review. Use when writing code that displays LLM output as authoritative fact, uses LLM decisions to gate consequential outcomes without human review, or builds automated pipelines where LLM judgment drives downstream actions.
Install
With your agent
Install OMGSkills skill "thejefflarson/soundcheck:.claude/skills/overreliance" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/thejefflarson/soundcheck /tmp/soundcheck && ln -s /tmp/soundcheck/.claude/skills/overreliance ~/.claude/skills/overrelianceFrom README
Overreliance on LLM Output (OWASP LLM09:2025) What this checks Prevents systems from treating LLM output as ground truth. LLMs hallucinate, produce confident-sounding errors, and lack real-time knowledge. Acting on unverified output in medical, legal, financial, or deployment contexts can cause serious harm. Vulnerable patterns LLM diagnosis, legal advice, or financial guidance displayed in the UI with no caveat or disclaimer. Automated pipeline that merges, deploys, or publishes based solely on an LLM approval signal. Confidence threshold defined as a constant but never used to branch behavior — every non-null response is accepted. High-stakes domain list defined but never compared against the current request before action. No alternate path when the LLM output fails a sanity check or confidence threshold. Fix immediately Flag the vulnerable code and explain the risk. Then suggest a fix that establishes these properties.
More from this repo
authentication-failures
Detects weak password storage, flawed JWT validation, sessions surviving logout, and missing MFA in authentication code.
broken-access-control
Detects missing ownership checks, broken role enforcement, and IDOR vulnerabilities that let users access other users'...
concurrency-correctness
Detects multi-threaded code where a lock is held across a blocking operation, lock acquisition order risks deadlock,...