security-defense
security-defense is an Agent security & guardrails skill for AI agents, published by smixs in the iva repository on GitHub. Skillspace rates security-defense F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Layered defense against prompt injection, data exfiltration, wallet drain, and cost overruns. Three runtime components: input sanitizer (Unicode/injection), outbound gate (secret leak prevention), spend governor (cost/volume limits). Use when processing external untrusted content (emails, webhooks, forwarded messages, web fetches, group chats), scanning outbound messages for leaked secrets, or monitoring LLM spend. Do NOT use for general security audits or penetration testing.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 54
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 84 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- exfiltration language
- accesses sensitive system files
- executes shell/subprocess
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.