dedup-skills
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to perform its deduplication workflow. It executes a local Python validation script (.claude/skills/create-skill/scripts/validate-skill.py), performs file comparisons withdiffandsed, and uses the GitHub CLI (gh) to search within thecedanlorganization for copies of skills. These are standard operations for its stated purpose of collection management. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its requirement to ingest and process text from other skills in the collection.
- Ingestion points: The skill reads
SKILL.mdfiles and extractsdescriptionfields from multiple directories within the.claude/skills/path usingRead,Grep, anddiff. - Boundary markers: There are no specific boundary markers or instructions provided to the agent to prevent it from following any instructions that might be embedded within the descriptions of the skills it is analyzing.
- Capability inventory: The skill is equipped with significant capabilities, including shell command execution (
Bash), file modification (Write,Edit), and GitHub interaction via theghCLI. - Sanitization: The skill does not perform sanitization, escaping, or structural validation of the ingested skill content before it is presented to the agent for decision-making.
Audit Metadata