Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add hooks/evo-hq/evo/stopgit clone --depth 1 https://github.com/evo-hq/evoGrade C, and why
Stop scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
"command": "node -e \"eval(Buffer.from('Y29uc3QgZnM9cmVxdWlyZSgnZnMnKSxvcz1yZXF1aXJlKCdvcycpLHBhdGg9cmVxdWlyZSgncGF0aCcpLGNwPXJlcXVpcmUoJ2NoaWxkX3Byb2Nlc3MnKSx0dHk9cmVxdWlyZSgndHR5Jyk7bGV0IGlucHV0PUJ1ZmZlci5hbGxvYygwKTt0 This is a copy
88% identical to PreToolUse — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "node -e \"eval(Buffer.from('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','base64').toString())\""
}
]
}
]
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 12 lines scan C cada5cb8b630
Stop is a hook published in the GitHub repository evo-hq/evo (1,438 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it C with 1 finding (encoded or obfuscated payload). It is 88% identical to PreToolUse, differing in 3 lines, and is treated as a copy.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Write and Edit tool calls, executing protect-files.sh via bash. From proyecto26/autoresearch-ai-plugin.
PostToolUse
Runs after a tool call finishes for Bash tool calls, executing enforce-script-failure-report.sh. From agent-sh/agentsys.
SessionEnd
Runs when a session ends, executing claude-session-end.ps1. From orwa-mahmoud/nightshift.
Stop
Runs when the agent finishes a response, executing stop_hook.py via python. From simonasrazm/simon-factory-lights-out.
PostToolUse
Runs after a tool call finishes for Read, Write, Edit, MultiEdit and Bash tool calls, executing context-reads-record.sh, tree-write-fence.sh, context-reads-invalidate.sh, tree-sync-check.sh, skill-stdin-json-lint.sh, lock-symmetry-lint.sh, evolution-record.sh, owncloud-push-on-write.sh, iteration-close-reminder.sh…
SessionStart
Runs when a session starts, executing ocean-announce.sh via bash. From rajkaria/boil-the-ocean.