wiki-page-writer
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git remote get-url originandgit rev-parse --abbrev-ref HEADvia the system shell to resolve repository URLs and branch names for the purpose of creating documentation citations.\n- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it is instructed to 'Read all relevant files' and 'Analyze' code paths to generate documentation. Maliciously crafted content within the analyzed source code files could potentially influence the agent's behavior.\n - Ingestion points: The skill reads source code files from the local repository during the analysis phase described in SKILL.md.\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the content of the analyzed files and its own instructional logic.\n
- Capability inventory: The agent has the ability to execute git commands and write files to the local file system.\n
- Sanitization: The skill does not perform any sanitization or validation of the content read from source files before analyzing them.
Audit Metadata