hig-technologies— agent skill

hig-technologies — independently scanned and version-tracked by SaferSkills.

by sinhoneyy·Agent Skill·github.com/sinhoneyy/master-skills

Is hig-technologies safe to install?

SaferSkills independently audited hig-technologies (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 · 34d 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 · plugins/master-skills-ai-agent-builder/skills/hig-technologies/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/master-skills-ai-agent-builder/skills/hig-technologies/SKILL.md· markdown
25### Payments and Commerce
26 
274. **Transparent and frictionless.** Standard Apple Pay button styles. Never ask for card de
… (108 chars elided on L27)
28 
29### Health and Fitness
Occurrences
1 occurrence · at L27
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/master-skills-ai-agent-builder/skills/hig-technologies/references/machine-learning.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/master-skills-ai-agent-builder/skills/hig-technologies/references/machine-learning.md· markdown
66 
67 
68Because people don’t ask for the results that a proactive feature provides, they may have le
… (107 chars elided on L68)
69 
70### [Visible or invisible](https://developer.apple.com/design/human-interface-guidelines/mac
… (35 chars elided on L70)
Occurrences
1 occurrence · at L68
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-01sha256c263e162a87e86d8rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/master-skills-ai-agent-builder/skills/hig-technologies/references/sign-in-with-apple.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
excerptplugins/master-skills-ai-agent-builder/skills/hig-technologies/references/sign-in-with-apple.md· markdown
48**Clarify whether the additional data you request is required or just recommended.** If the
… (108 chars elided on L48)
49 
50**Don’t ask people to supply a password.** A key benefit of Sign in with Apple is that peopl
… (108 chars elided on L50)
51 
52**Avoid asking for a personal email address when people supply a private relay address.** Us
… (108 chars elided on L52)
Occurrences
2 occurrences · first at L50, also L50
Show all 2 locations
Line
File
L50
plugins/master-skills-ai-agent-builder/skills/hig-technologies/references/sign-in-with-apple.md
L50
plugins/master-skills-ai-agent-builder/skills/hig-technologies/references/sign-in-with-apple.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-01sha2567fd804810fbc46dfrubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/master-skills-ai-agent-builder/skills/hig-technologies/references/siri.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/master-skills-ai-agent-builder/skills/hig-technologies/references/siri.md· markdown
228**Design your intents to be long-lived.** Avoid offering intents that are date-specific or a
… (108 chars elided on L228)
229 
230**Don’t request permission to use Siri.** If your app supports only custom intents — and not
… (108 chars elided on L230)
231 
232**Support background operation.** The best intents support shortcuts that run quickly and do
… (108 chars elided on L232)
Occurrences
1 occurrence · at L230
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-01sha2563e1e6f83da98a28crubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/master-skills-ai-agent-builder/skills/hig-technologies/references/wallet.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/master-skills-ai-agent-builder/skills/hig-technologies/references/wallet.md· markdown
17**Offer to add new passes to Wallet.** When people do something that results in a new pass —
… (108 chars elided on L17)
18 
19**Help people add a pass that they created outside of your app.** If people create a pass us
… (107 chars elided on L19)
20 
21**Add related passes as a group.** If your app generates multiple passes, like boarding pass
… (108 chars elided on L21)
Occurrences
1 occurrence · at L19
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-01sha256c263e162a87e86d8rubric 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.