product-photo-studio— agent skill

product-photo-studio — independently scanned and version-tracked by SaferSkills.

by PicsArt·Agent Skill·github.com/PicsArt/gen-ai-skills

Is product-photo-studio safe to install?

SaferSkills independently audited product-photo-studio (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 · skills/product-photo-studio/references/modes/bulk-restyle.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
excerptskills/product-photo-studio/references/modes/bulk-restyle.md· markdown
89- **SKU → filename convention.** `SKU-001_4x5.webp`, `SKU-001_1x1.webp`, `SKU-001_9x16.webp`
… (31 chars elided on L89)
90- **Keep the source untouched.** Write to `./styled/`, not over `./raw/`. `gen-ai batch resu
… (47 chars elided on L90)
91- **One aspect per pass.** Don't ask one call for 3 aspects — run 3 batches sharing the same
… (49 chars elided on L91)
92- **Gate with `brand.md`** on every job so banned props/colors are caught before spend.
93- **Sample-QA 5%** before delivering. A drifted shadow direction across 1000 SKUs is a PDP-w
… (13 chars elided on L93)
Occurrences
1 occurrence · at L91
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 · skills/product-photo-studio/references/modes/mockups.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
excerptskills/product-photo-studio/references/modes/mockups.md· markdown
111## Procedure
112 
113- **One surface per job.** Never prompt "tee AND mug AND poster" in one call.
114- **Use the phrase "the same [artwork / logo / design]"** when passing `-i` — models respond
… (36 chars elided on L114)
115- **Describe the scene, not the photo.** "Morning light through a linen curtain, shallow DoF
… (54 chars elided on L115)
Occurrences
2 occurrences · first at L113, also L126
Show all 2 locations
Line
File
L113
skills/product-photo-studio/references/modes/mockups.md
L126
skills/product-photo-studio/references/modes/mockups.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-01sha256c6ccbeff3f20088crubric 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.