SkillSpector · src-hunter

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

references/payloader/by-category/web/供应链攻击.md

Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

references/payloader/raw/tools.json

Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

references/payloader/tools/web渗透.md

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

references/playbooks/rce.md

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

references/payloader/by-category/web/ai安全.md

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

references/payloader/by-category/web/ai安全.md

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

references/payloader/by-category/web/ai安全.md

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

references/playbooks/llm-prompt-injection.md

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

references/playbooks/llm-prompt-injection.md

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

references/playbooks/llm-prompt-injection.md

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

references/payloader/raw/tools.json

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

LICENSE

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

README.en.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

README.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/methodology/01-attack-priority.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/methodology/02-bypass-toolkit.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/methodology/02-bypass-toolkit.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/methodology/03-evidence-discipline.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/methodology/04-control-gap-hunting.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/methodology/04-control-gap-hunting.md