liberfi-predict— agent skill

liberfi-predict — independently scanned and version-tracked by SaferSkills.

by liberfi-io·Agent Skill·github.com/liberfi-io/liberfi-skills

Is liberfi-predict safe to install?

SaferSkills independently audited liberfi-predict (Agent Skill) and scored it 79/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 5 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
79/100
●●●●●●●●○○
↑ +0 since first scan (79 → 79)Re-scan~30s
Latest scan
ScannedJun 28, 2026 · 31d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings5 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
40
14.0 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 · 5 flagged

Securityscore 40 · 5 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/liberfi-predict/SKILL.md×5
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
excerptskills/liberfi-predict/SKILL.md· markdown
40CRITICAL: For ANY first-person prediction query — "我现在押了哪些",
41"我在预测市场赚了多少", "my positions", "my balance", "我的盈亏",
42"我在 Polymarket 上的钱" — DO NOT ask the user for a wallet address.
43Run this exact sequence: (1) `lfi status --json`, (2) if not authed,
44`lfi login key --role AGENT --name "OpenClawAgent" --json`, (3)
Occurrences
5 occurrences · first at L42, also L370, L405 +2 more
Show all 5 locations
Line
File
L42
skills/liberfi-predict/SKILL.md
L370
skills/liberfi-predict/SKILL.md
L405
skills/liberfi-predict/SKILL.md
L418
skills/liberfi-predict/SKILL.md
L432
skills/liberfi-predict/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-01sha2563507b488e8245eb0rubric 365aacaView on GitHub
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.