rescue— agent skill

rescue — independently scanned and version-tracked by SaferSkills.

by ·Agent Skill·github.com/null/null

Is rescue safe to install?

SaferSkills independently audited rescue (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
83/100
●●●●●●●●○○
↑ +0 since first scan (83 → 83)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 29d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings4 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
52
18.2 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 4 flagged

Securityscore 52 · 4 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · claude-code/plugins/openai-codex__codex/commands/rescue/SKILL.md×4
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptclaude-code/plugins/openai-codex__codex/commands/rescue/SKILL.md· markdown
19- `--background` and `--wait` are execution flags for Claude Code. Do not forward them to `t
… (70 chars elided on L19)
20- `--model` and `--effort` are runtime-selection flags. Preserve them for the forwarded `tas
… (73 chars elided on L20)
21- If the request includes `--resume`, do not ask whether to continue. The user already chose
… (1 chars elided on L21)
22- If the request includes `--fresh`, do not ask whether to continue. The user already chose.
23- Otherwise, before starting Codex, check for a resumable rescue thread from this Claude ses
… (16 chars elided on L23)
Occurrences
4 occurrences · first at L21, also L22, L37 +1 more
Show all 4 locations
Line
File
L21
claude-code/plugins/openai-codex__codex/commands/rescue/SKILL.md
L22
claude-code/plugins/openai-codex__codex/commands/rescue/SKILL.md
L37
claude-code/plugins/openai-codex__codex/commands/rescue/SKILL.md
L44
claude-code/plugins/openai-codex__codex/commands/rescue/SKILL.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25612211d7a427c799arubric 365aaca
Supply chainscore 100 · 0 findings
All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.