← back to ce-pov

SkillSpector · ce-pov

independent scanner by NVIDIA · skill by thedixitjain · how it works ↗

FAILmax severity: CRITICALrisk score: 100

subprocess module calls execute external commands. Without careful input validation, this enables command injection.; Without declared permissions the skill's intent is opaque and cannot be validated.; Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, a…; +6 more

scanned 2026-08-23

Findings (20)

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/peer-job-runner.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/peer-job-runner.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/peer-job-runner.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/peer-job-runner.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/peer-job-runner.py

MEDIUMMCP Least Privilegeconfidence: 0.7

Without declared permissions the skill's intent is opaque and cannot be validated.

SKILL.md

MEDIUMAgent Snoopingconfidence: 0.8

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

SKILL.md

MEDIUMAgent Snoopingconfidence: 0.8

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

SKILL.md

MEDIUMAgent Snoopingconfidence: 0.8

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

SKILL.md

MEDIUMExcessive Agencyconfidence: 0.75

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

scripts/peer-job-runner.py

MEDIUMOutput Handlingconfidence: 0.75

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

scripts/cross-model-pov.sh

HIGHOutput Handlingconfidence: 0.95

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

scripts/peer-job-runner.py

MEDIUMPrivilege Escalationconfidence: 0.8

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

SKILL.md

MEDIUMPrivilege Escalationconfidence: 0.8

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

scripts/cross-model-pov.sh

MEDIUMPrivilege Escalationconfidence: 0.8

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

scripts/cross-model-pov.sh

MEDIUMPrivilege Escalationconfidence: 0.8

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

scripts/cross-model-pov.sh

MEDIUMPrivilege Escalationconfidence: 0.8

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

scripts/cross-model-pov.sh

MEDIUMPrivilege Escalationconfidence: 0.8

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

scripts/peer-job-runner.py

MEDIUMRogue Agentconfidence: 0.65

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

scripts/peer-job-runner.py

MEDIUMRogue Agentconfidence: 0.65

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

scripts/peer-job-runner.py

What the verdicts mean

SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.

PASS

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete