Files
skills/tests/mcp_destructive_guard_test.sh
T
mathiasandClaude Opus 5.5 4a82206393
CI / Check / Test (push) Successful in 4s
CI / Tag release (push) Skipped
CI / Check / Test (pull_request) Successful in 5s
CI / Tag release (pull_request) Skipped
fix(hooks): close the five escapes the skills#52 review found
- Fail-closed path no longer needs jq: the ask JSON is a printf literal,
  and a host without jq asks instead of staying silent.
- A tool_name that is not a non-empty string asks (was: no opinion).
- Gate workflow_run_trigger, tag_create, release_create, and
  file_write_branch when it lands on main/master, has no branch, or
  empties a file (same effect as pr_merge / file_delete).
- Header claim narrowed: gitea-mcp spellings on any server name, not
  other servers' spellings of the same operation.
- Tests run the hook as hooks.json does (bash <path>), assert exit 0 on
  every case, and cover null/missing/wrong-type tool_name, last-segment
  verb parsing and a PATH without jq. 13 new cases were red first.

Refs mathias/infra#508

Bump-Type: minor

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-01 20:45:19 +02:00

100 lines
4.9 KiB
Bash
Executable File

#!/bin/sh
# Tests for hooks/mcp-destructive-guard.sh — the PreToolUse gate that makes a
# human approve irreversible MCP verbs (infra#508, infra ADR-0027).
#
# Contract: reads PreToolUse hook JSON on stdin, ALWAYS exits 0, and answers
# in hookSpecificOutput.permissionDecision. "ask" = a human must approve;
# empty stdout ("NONE") = no opinion, normal permission rules apply. The guard
# never emits "allow": an allow from a hook would bypass the user's own rules.
#
# Cases marked (gatekeeper) are escapes found by the skills#52 review: each
# passed the first version of this suite.
set -u
ROOT=$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)
GUARD="$ROOT/hooks/mcp-destructive-guard.sh"
pass=0
fail=0
# run_guard <json> [PATH] — invoked exactly as hooks.json does: `bash <path>`.
# Prints "<decision> rc=<exit>", decision NONE for an empty answer.
run_guard() {
if [ $# -ge 2 ]; then
_out=$(printf '%s' "$1" | PATH="$2" "$BASH_BIN" "$GUARD"); _rc=$?
else
_out=$(printf '%s' "$1" | bash "$GUARD"); _rc=$?
fi
if [ -z "$_out" ]; then _d=NONE
else _d=$(printf '%s' "$_out" | jq -r '.hookSpecificOutput.permissionDecision // "NONE"' 2>/dev/null || echo BROKEN)
fi
printf '%s rc=%s' "$_d" "$_rc"
}
BASH_BIN=$(command -v bash)
check() {
_want=$1 _json=$2 _label=$3
_got=$(run_guard "$_json")
if [ "$_got" = "$_want rc=0" ]; then
pass=$((pass + 1)); printf ' ok %s\n' "$_label"
else
fail=$((fail + 1)); printf ' FAIL %s\n want=%s rc=0 got=%s\n in=%s\n' "$_label" "$_want" "$_got" "$_json"
fi
}
tool() { printf '{"tool_name":"%s","tool_input":{"owner":"mathias","repo":"x"}}' "$1"; }
echo "mcp-destructive-guard tests"
for v in repo_delete file_delete branch_delete pr_merge tbd_ship repo_update repo_mirror_push \
workflow_run_trigger tag_create release_create; do
check ask "$(tool "mcp__plugin_skills_gitea__$v")" "plugin gitea $v asks"
done
# The verb is matched on any server name: connector, bare, or renamed.
check ask "$(tool mcp__claude_ai_gitea__repo_delete)" "connector namespace asks"
check ask "$(tool mcp__gitea__repo_delete)" "bare server name asks"
check ask "$(tool mcp__git__repo_delete)" "renamed server still asks"
check ask "$(tool mcp__plugin_skills_gitea__REPO_DELETE)" "uppercase verb asks"
# The verb is the LAST segment (gatekeeper: parsing the second segment stayed green).
check ask "$(tool mcp__a__b__repo_delete)" "verb taken from last segment"
check NONE "$(tool mcp__repo_delete__issue_get)" "server named like a verb does not trigger"
# file_write_branch: content landing on main, or emptying a file, is the same
# effect as the gated pr_merge / file_delete (gatekeeper).
fwb() { printf '{"tool_name":"mcp__plugin_skills_gitea__file_write_branch","tool_input":{"branch":"%s","content":"%s"}}' "$1" "$2"; }
check ask "$(fwb main x)" "file_write_branch to main asks"
check ask "$(fwb master x)" "file_write_branch to master asks"
check ask "$(fwb feat/y '')" "file_write_branch emptying a file asks"
check ask '{"tool_name":"mcp__plugin_skills_gitea__file_write_branch","tool_input":{"content":"x"}}' "file_write_branch without branch asks"
check NONE "$(fwb feat/y x)" "file_write_branch to a feature branch passes"
# Reversible / read verbs pass through.
for v in issue_close issue_create file_read repo_list pr_create; do
check NONE "$(tool "mcp__plugin_skills_gitea__$v")" "$v passes through"
done
check NONE "$(tool mcp__plugin_skills_gitea__repo_delete_dry_run_list)" "suffix near-miss passes"
check NONE "$(tool Bash)" "non-MCP tool passes"
check NONE "$(tool repo_delete)" "non-MCP tool named like a verb passes"
# Malformed input fails CLOSED (gatekeeper: non-string tool_name got NONE).
check ask 'not json' "non-JSON asks"
check ask '{}' "missing tool_name asks"
check ask '{"tool_name":null}' "null tool_name asks"
check ask '{"tool_name":""}' "empty tool_name asks"
check ask '{"tool_name":5}' "number tool_name asks"
check ask '{"tool_name":["mcp__x__repo_delete"]}' "array tool_name asks"
check ask '{"tool_name":{"a":1}}' "object tool_name asks"
# Without jq on PATH the guard must still answer ask, not stay silent
# (gatekeeper: the fail-closed path itself needed jq).
nojq=$(mktemp -d); trap 'rm -rf "$nojq"' EXIT
for b in bash cat grep tr sed; do ln -s "$(command -v $b)" "$nojq/$b"; done
_got=$(run_guard "$(tool mcp__plugin_skills_gitea__repo_delete)" "$nojq")
if [ "$_got" = "ask rc=0" ]; then pass=$((pass+1)); echo " ok no jq on PATH still asks"; else fail=$((fail+1)); echo " FAIL no jq on PATH: got=$_got"; fi
_got=$(run_guard "$(tool mcp__plugin_skills_gitea__issue_get)" "$nojq")
if [ "$_got" = "ask rc=0" ]; then pass=$((pass+1)); echo " ok no jq on PATH asks even for a read verb (cannot parse = cannot clear)"; else fail=$((fail+1)); echo " FAIL no jq read verb: got=$_got"; fi
printf '\n%d passed, %d failed\n' "$pass" "$fail"
[ "$fail" -eq 0 ]