Socialperks— agent skill

Socialperks — independently scanned and version-tracked by SaferSkills.

by benzatkulak-collab·Agent Skill·github.com/benzatkulak-collab/socialperks

Is Socialperks safe to install?

SaferSkills independently audited Socialperks (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
87/100
●●●●●●●●●
↑ +0 since first scan (87 → 87)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 34d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings3 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
64
22.4 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 · 3 flagged

Securityscore 64 · 3 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · audit/reinvention/09-conversion-funnel.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
excerptaudit/reinvention/09-conversion-funnel.md· markdown
45## 4. The paid-conversion trigger design (when/how to ask for money)
46 
47- **Don't ask at signup** (the current pricing-intent path 503s anyway). Ask at the **value
… (108 chars elided on L47)
48- Add **success-based** prompts (none exist today — all current triggers are scarcity-based)
… (54 chars elided on L48)
49- Make the **door reachable**: billing link in nav; one-click upgrade that uses `subscriptio
… (35 chars elided on L49)
Occurrences
1 occurrence · at L47
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-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · docs/distribution/announcement-posts.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
excerptdocs/distribution/announcement-posts.md· markdown
114 
115**Don't:**
116- Don't ask for upvotes anywhere (Discord, X, etc.) — HN flags this
117- Don't use exclamation marks or marketing language in the title
118- Don't re-submit if the first attempt flames out — wait a week
Occurrences
1 occurrence · at L116
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-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · docs/launch-submissions/04-hacker-news.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
excerptdocs/launch-submissions/04-hacker-news.md· markdown
85- Don't post your bio / company history
86- Don't link to a paywalled or auth-gated landing
87- Don't ask for upvotes anywhere (HN actively penalizes vote
88manipulation)
89 
Occurrences
1 occurrence · at L87
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-01sha25615dae9807bd892c6rubric 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.