gcc-market-intelligence— agent skill

Open Claude Skill for B2B/B2G founders entering the GCC — Saudi, UAE, Qatar, Bahrain, Kuwait, Oman. Families, sovereign funds, soft-landing, procurement, localization.

Is gcc-market-intelligence safe to install?

SaferSkills independently audited gcc-market-intelligence (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
83/100
●●●●●●●●○○
↑ +0 since first scan (83 → 83)Re-scan~30s
Latest scan
ScannedJun 28, 2026 · 30d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings4 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
52
18.2 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 · 4 flagged

Securityscore 52 · 4 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · gcc-market-intelligence/references/culture/customer-development.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
excerptgcc-market-intelligence/references/culture/customer-development.md· markdown
202 
203- ❌ Don't follow up the same day. Wait at least 24 hours.
204- ❌ Don't ask for an NDA at first meeting. It implies distrust. Wait until you're in a real
… (27 chars elided on L204)
205- ❌ Don't ghost a junior contact. They often become your primary advocate internally.
206- ❌ Don't use slide decks with US-only logos / US-centric data. Localize before every GCC me
… (6 chars elided on L206)
Occurrences
2 occurrences · first at L204, also L207
Show all 2 locations
Line
File
L204
gcc-market-intelligence/references/culture/customer-development.md
L207
gcc-market-intelligence/references/culture/customer-development.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-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · gcc-market-intelligence/references/families/how-to-approach-families.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
excerptgcc-market-intelligence/references/families/how-to-approach-families.md· markdown
1167. **Don't shake hands with women** unless they extend theirs first.
1178. **Don't refuse food, coffee, or hospitality** offered. Even small refusals can offend.
1189. **Don't ask for the patriarch's direct number / email.** Communicate via the executive of
… (5 chars elided on L118)
11910. **Don't post photos with family principals** to social media without explicit permission
… (45 chars elided on L119)
12011. **Don't reference family disputes, succession battles, or personal lives.** Strictly com
… (15 chars elided on L120)
Occurrences
1 occurrence · at L118
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
MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · gcc-market-intelligence/references/families/saudi-merchant-families.md
MEDIUMit fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.
Why it matters

A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.

The exact value spotted
excerptgcc-market-intelligence/references/families/saudi-merchant-families.md· markdown
133 
134- Don't gossip about other families. Word travels in days.
135- Don't reveal what one family told you to another family. Confidentiality is a reputational
… (10 chars elided on L135)
136- Don't try to negotiate hard on a first deal — early deals are relationship investments, no
… (25 chars elided on L136)
137- Don't bring up family disputes, successions, or inheritance battles. Not your topic.
Occurrences
1 occurrence · at L135
How to fix
Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.
  1. Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
  2. Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IMPERATIVE-01sha2565934d26e507bfe15rubric 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.