llm-wiki-persona— agent skill

llm-wiki-persona — independently scanned and version-tracked by SaferSkills.

by anh-chu·Agent Skill·github.com/anh-chu/llm-wiki-pm

Is llm-wiki-persona safe to install?

SaferSkills independently audited llm-wiki-persona (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
96/100
●●●●●●●●●●
Re-scan~30s
Latest scan
ScannedJun 28, 2026 · 130d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings1 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
88
30.8 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 · 1 flagged

Securityscore 88 · 1 finding
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/llm-wiki-persona/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
excerptskills/llm-wiki-persona/SKILL.md· markdown
47② **Gather source material**: proactively search connected comms tools first
48(chat search, email search, meeting notes) for the person's name and
49email/handle, THEN confirm channels with the user. Don't ask the user to hand
50you material you can retrieve yourself. Ingest the threads via the core skill's
51§2 Ingest flow before writing the persona page. A persona built only from
Occurrences
1 occurrence · at L49
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.