three-minute-email— agent skill

three-minute-email — independently scanned and version-tracked by SaferSkills.

by miniminer-droid·Agent Skill·github.com/miniminer-droid/skill-locker-free

Is three-minute-email safe to install?

SaferSkills independently audited three-minute-email (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 24, 2026 · 32d 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 · plugins/skill-locker-free/skills/three-minute-email/SKILL.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
excerptplugins/skill-locker-free/skills/three-minute-email/SKILL.md· markdown
164- **Never use a formal tone "just to be safe."** Overly formal emails between people who kno
… (53 chars elided on L164)
165- **Never include a disclaimer or caveat unless the user asks for one.** "Of course, every s
… (70 chars elided on L165)
166- **Never ask more than one clarifying question.** If you have enough context to write (who
… (107 chars elided on L166)
Occurrences
1 occurrence · at L166
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 · plugins/skill-locker-free/skills/three-minute-email/versions/v1.0.0.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
excerptplugins/skill-locker-free/skills/three-minute-email/versions/v1.0.0.md· markdown
122- **Never use a formal tone "just to be safe."** Overly formal emails between people who kno
… (53 chars elided on L122)
123- **Never include a disclaimer or caveat unless the user asks for one.** "Of course, every s
… (70 chars elided on L123)
124- **Never ask more than one clarifying question.** If the user's description is vague, write
… (108 chars elided on L124)
Occurrences
1 occurrence · at L124
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 · plugins/skill-locker-free/skills/three-minute-email/versions/v1.1.0.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
excerptplugins/skill-locker-free/skills/three-minute-email/versions/v1.1.0.md· markdown
134- **Never use a formal tone "just to be safe."** Overly formal emails between people who kno
… (53 chars elided on L134)
135- **Never include a disclaimer or caveat unless the user asks for one.** "Of course, every s
… (70 chars elided on L135)
136- **Never ask more than one clarifying question.** If you have enough context to write (who
… (107 chars elided on L136)
Occurrences
1 occurrence · at L136
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 · plugins/skill-locker-free/skills/three-minute-email/versions/v1.2.0.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
excerptplugins/skill-locker-free/skills/three-minute-email/versions/v1.2.0.md· markdown
143- **Never use a formal tone "just to be safe."** Overly formal emails between people who kno
… (53 chars elided on L143)
144- **Never include a disclaimer or caveat unless the user asks for one.** "Of course, every s
… (70 chars elided on L144)
145- **Never ask more than one clarifying question.** If you have enough context to write (who
… (107 chars elided on L145)
Occurrences
1 occurrence · at L145
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 · plugins/skill-locker-free/skills/three-minute-email/versions/v1.3.0.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
excerptplugins/skill-locker-free/skills/three-minute-email/versions/v1.3.0.md· markdown
164- **Never use a formal tone "just to be safe."** Overly formal emails between people who kno
… (53 chars elided on L164)
165- **Never include a disclaimer or caveat unless the user asks for one.** "Of course, every s
… (70 chars elided on L165)
166- **Never ask more than one clarifying question.** If you have enough context to write (who
… (107 chars elided on L166)
Occurrences
1 occurrence · at L166
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
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.