update-docs
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
exec:bashto interact with the git version control system, includinggit log,git diff,git add,git commit, andgit push.- [DATA_EXFILTRATION]: The skill transmits documentation updates to the remote repository usinggit push -u origin HEAD. This is the intended behavior for synchronizing the project's documentation with its source of truth.- [PROMPT_INJECTION]: The skill represents an indirect prompt injection surface because it ingests and processes data from the local environment that may be influenced by external inputs or previous automated tasks. - Ingestion points: The skill reads contents from
README.md,CLAUDE.md,docs/index.html, andplugforge-starter/agents/gm.md, as well as output fromgit logandgit diff. - Boundary markers: The skill does not employ specific delimiters or instructions to ignore potential embedded commands within the files it reads.
- Capability inventory: The skill possesses file-system write access (
fs.writeFileSync) and command execution capabilities (gitcommands). - Sanitization: There is no evidence of filtering or sanitizing the content read from disk before it is processed by the agent to generate documentation updates.
Audit Metadata