← back to alpaca

SkillSpector · alpaca

independent scanner by NVIDIA · skill by kbarbel640-del · how it works ↗

WARNINGmax severity: HIGHrisk score: 59

Without declared permissions the skill's intent is opaque and cannot be validated.; Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.; Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain…; +1 more

scanned 2026-08-22

Findings (7)

MEDIUMMCP Least Privilegeconfidence: 0.7

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

SKILL.md

HIGHData Exfiltrationconfidence: 0.7

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

scripts/alpaca_cli.py

HIGHData Exfiltrationconfidence: 0.7

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

scripts/alpaca_cli.py

MEDIUMRogue Agentconfidence: 0.6

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/alpaca_cli.py

HIGHTool Misuseconfidence: 0.24

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

references/api.md

HIGHTool Misuseconfidence: 0.24

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

references/api.md

HIGHTool Misuseconfidence: 0.24

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

references/api.md

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

WARNINGthis skill

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete