elon— agent skill

elon — independently scanned and version-tracked by SaferSkills.

by Democraitus·Agent Skill·github.com/Democraitus/elons-brain

Is elon safe to install?

SaferSkills independently audited elon (Agent Skill) and scored it 75/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 6 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
75/100
●●●●●●●●○○
↑ +0 since first scan (75 → 75)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 31d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings6 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
28
9.8 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 · 6 flagged

Securityscore 28 · 6 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · elon/skills/expect-loss/MODEL.md×2
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
excerptelon/skills/expect-loss/MODEL.md· markdown
59Expected loss is the cold input. Operational optimism is the daily fuel. Hold both.
60 
617. **If you would not risk your own money, do not ask investors to risk theirs.**
62> "Don't ask investors to invest their money if you're not prepared to invest your money. It
… (105 chars elided on L62)
63> — *The Book of Elon*
Occurrences
2 occurrences · first at L61, also L62
Show all 2 locations
Line
File
L61
elon/skills/expect-loss/MODEL.md
L62
elon/skills/expect-loss/MODEL.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 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · elon/skills/frontline-leadership/MODEL.md
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
excerptelon/skills/frontline-leadership/MODEL.md· markdown
11## What this skill captures
12 
13Leadership is physical presence at the worst part of the problem, not a Slack message from a
… (107 chars elided on L13)
14 
15The value: you stop deluding yourself that "trusting the team" is leadership when it's actua
… (107 chars elided on L15)
Occurrences
1 occurrence · at L13
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-01sha2565084aa178cfd9d97rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · elon/skills/invest-your-money-first/MODEL.md×3
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
excerptelon/skills/invest-your-money-first/MODEL.md· markdown
1---
2name: invest-your-money-first
3description: Force the founder skin-in-the-game ethics test before any fundraise. Use this s
… (107 chars elided on L3)
4---
5 
Occurrences
3 occurrences · first at L3, also L13, L29
Show all 3 locations
Line
File
L3
elon/skills/invest-your-money-first/MODEL.md
L13
elon/skills/invest-your-money-first/MODEL.md
L29
elon/skills/invest-your-money-first/MODEL.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-01sha256ce5204b52388d24frubric 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.