source-command-dedupe
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, untrusted data from GitHub issues, which represents an indirect prompt injection surface where malicious instructions in an issue could influence the agent's summarization or filtering steps. \n
- Ingestion points: The skill reads GitHub issue content via the
ghcommand-line tool (SKILL.md). \n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are specified for the ingested content. \n
- Capability inventory: The agent has permissions to read repository data, perform searches, and post comments via the
ghtool (SKILL.md). \n - Sanitization: There is no evidence of sanitization or validation of the fetched issue content before it is passed to agents for processing.
Audit Metadata