skill-deep-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (the skill being reviewed) which could contain instructions designed to manipulate the auditing agent.
- Ingestion points: Reads the content of
SKILL.mdand all files within the target skill's directory tree during Phase 1. - Boundary markers: Absent. There are no explicit instructions or delimiters defined to isolate the audited content from the reviewer's own execution context or to warn the agent to ignore instructions embedded within the files being reviewed.
- Capability inventory: The skill uses
Bash,Read,Grep, andGlobtools to perform analysis and save a report to the file system. - Sanitization: Absent. There is no mention of sanitizing or escaping the content of the reviewed skill before it is processed or included in the final markdown report.
Audit Metadata