time-registration— agent skill

time-registration — independently scanned and version-tracked by SaferSkills.

by rvanbaalen·Agent Skill·github.com/rvanbaalen/skills

Is time-registration safe to install?

SaferSkills independently audited time-registration (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
92/100
●●●●●●●●●○
Re-scan~30s
Latest scan
ScannedJun 26, 2026 · 130d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings2 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
76
26.6 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 · 2 flagged

Securityscore 76 · 2 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/time-registration/skills/time-registration/SKILL.md
MEDIUM — it 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/time-registration/skills/time-registration/SKILL.md· markdown
68 
69- `"zoho"` — log to Zoho in step 10, using the saved `zoho` settings. If the detected Zoho t
… (108 chars elided on L69)
70- `"clipboard"` — the user declined Zoho. Don't ask about Zoho again; offer the clipboard in
… (9 chars elided on L70)
71- Not set — check whether a Zoho Invoice MCP is connected (a tool whose name ends in `ZohoIn
… (108 chars elided on L71)
72 
Occurrences
1 occurrence · at L70
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-01sha25615dae9807bd892c6…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/time-registration/skills/time-registration/zoho.md
MEDIUM — it 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/time-registration/skills/time-registration/zoho.md· markdown
231. **Use Zoho?** `Log time for <project> in Zoho Invoice?` with `Yes, log to Zoho` / `No, ju
… (108 chars elided on L23)
242. **Organization.** Call `List_all_Organizations`. With one organization, use it. With seve
… (66 chars elided on L24)
253. **User.** Call `Get_the_Current_User` and keep `user.user_id`. Don't ask.
264. **Project.** Call `List_all_Projects` with `filter_by: Status.Active`. Score each Zoho pr
… (107 chars elided on L26)
275. **Task.** Call `List_all_Tasks_of_a_Project` for the chosen project and ask which task to
… (89 chars elided on L27)
Occurrences
1 occurrence · at L25
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-01sha25615dae9807bd892c6…rubric 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.